A method, medium and system for intelligently monitoring bubble-shaped green spots in the airing of cigar tobacco

Abstract

The present application relates to the technical field of tobacco monitoring, and discloses a method, medium and system for intelligently monitoring bubble-shaped green spots in the airing of cigar tobacco, which comprises: obtaining image information of bubble-shaped green spots in the airing of each cigar tobacco, and establishing a bubble-shaped green spot feature set according to the characteristics thereof. Subsequently, the surface images of each cigar tobacco in the airing area are obtained, and feature matching is performed. When the surface image features match the bubble-shaped green spot features, the tobacco is determined to be a sick tobacco. Based on the number and grade of sick tobacco, the early warning score of the airing area is calculated. At the same time, the illumination of each tobacco, and the environmental temperature and humidity of the airing area are obtained, so as to adjust the early warning score. Finally, according to the adjusted early warning score, the early warning grade of the airing area is determined. The present application combines image analysis and environmental monitoring, aiming to effectively warn and manage tobacco diseases.

Description

Technical Field

[0001] This invention relates to the field of tobacco leaf monitoring technology, and more specifically, to a method, medium, and system for intelligent monitoring of blister-like green spots during the drying of cigar tobacco leaves. Background Technology

[0002] High-quality cigar tobacco leaves are the foundation for making high-quality cigars, especially the wrapper tobacco, the outermost layer of the cigar leaf, which is the "face" of a cigar. The color, veins, tension, oiliness, and flavor of the wrapper can largely determine the value of a cigar. Currently, China relies almost entirely on imports for its cigar wrappers. Despite significant efforts to develop domestic cigar tobacco leaf production in recent years, the production of high-quality wrappers is constrained by the availability of premium raw materials. However, the common occurrence of blistering "green spots" during the cigar drying process significantly impacts the production of premium wrappers.

[0003] Currently, the detection of "green spots" during cigar drying mainly relies on manual inspection of the curing barns. Each leaf is examined individually to determine if it exhibits the phenotype of "green spots," and then the drying process is adjusted accordingly to reduce the phenomenon. However, this traditional manual inspection method has several problems: Standard curing barns typically have 5-7 layers of tobacco leaves, measuring over 20 meters long and 10 meters wide. During the drying process, the humidity, perceived temperature, and air irritation inside are high. Inspecting a single barn takes at least 1-2 hours per person, and the prolonged work at height significantly increases the risk of falls. Secondly, the detection of green spots relies on portable artificial light sources such as flashlights. In the early stages of green spot formation, the phenotype is not obvious, and accurate judgment is difficult to make with the human eye in low light conditions. Furthermore, it requires staff to have extensive experience in cigar tobacco drying to improve the accuracy of the detection.

[0004] Therefore, there is an urgent need to invent a technology for monitoring blistering spots during the drying process of cigar tobacco leaves, in order to solve the problems of low efficiency, poor accuracy and safety risks in monitoring blisters caused by relying on manual inspections during the cigar drying process in the existing technology. Summary of the Invention

[0005] In view of this, the present invention proposes an intelligent monitoring method, medium and system for blistering in cigar tobacco leaf drying, aiming to solve the problems of low efficiency, poor accuracy and safety risks in monitoring blisters caused by reliance on manual inspection during cigar drying in the current technology.

[0006] This invention proposes an intelligent monitoring method for blister-like green spots during cigar tobacco leaf drying, comprising:

[0007] Image information of blister-like green spots during the drying of each cigar tobacco leaf is obtained, and a blister-like green spot feature set is established based on the blister-like green spot features in each image information.

[0008] acquiring surface image of each cigar leaf in the airing area, and matching between the surface image features and the blister spot features according to the blister spot features;

[0009] when the surface image features match the blister spot features, determining that the cigar leaf corresponding to the surface image features is a sick leaf, and acquiring the area and quantity of the blister spot features in the sick leaf, and determining the blister spot density of the sick leaf according to the area and quantity of the blister spot features and the area of the sick leaf;

[0010] determining the sick grade of the sick leaf according to the blister spot density, wherein the sick grade is sequentially a first sick grade, a second sick grade and a third sick grade;

[0011] determining the early warning score of the airing area according to the quantity of the sick leaf in the airing area and the sick grade of each sick leaf;

[0012] acquiring the illumination of each cigar leaf in the airing area, the environmental temperature and the environmental humidity of the airing area, and adjusting the early warning score according to the illumination of each cigar leaf, the environmental temperature and the environmental humidity of the airing area;

[0013] acquiring the adjusted early warning score, and determining the early warning grade of the airing area according to the relationship between the adjusted early warning score and a first preset early warning score and a second preset early warning score, wherein:

[0014] when the adjusted early warning score is less than the first preset early warning score, determining that the early warning grade of the airing area is a low risk grade;

[0015] when the adjusted early warning score is greater than or equal to the first preset early warning score and less than the second preset early warning grade, determining that the early warning grade of the airing area is a medium risk grade;

[0016] when the adjusted early warning score is greater than or equal to the second preset early warning score, determining that the early warning grade of the airing area is a high risk grade.

[0017] Further, when determining the early warning score of the airing area according to the quantity of the sick leaf in the airing area and the sick grade of each sick leaf, comprising:

[0018] obtaining the number of the first disease level tobacco leaves, the number of the second disease level tobacco leaves and the number of the third disease level tobacco leaves, and substituting the number of the first disease level tobacco leaves, the number of the second disease level tobacco leaves and the number of the third disease level tobacco leaves into Formula I to determine the early warning score of the curing area, the Formula I being as follows:

[0019] P=z1×Q+z2×K+z3×J;

[0020] wherein P is the early warning score of the curing area, Q is the number of the first disease level tobacco leaves, K is the number of the second disease level tobacco leaves, J is the number of the third disease level tobacco leaves, z1-z3 are weight coefficients, and the sum of z1-z3 is 1.

[0021] Further, when adjusting the early warning score according to the illumination of each of the cigar leaves, the environmental temperature and the environmental humidity of the curing area, the method comprises:

[0022] obtaining the illumination area of each of the cigar leaves in a preset period, and determining the illumination proportion of each of the cigar leaves according to the illumination area and the area of the cigar leaves;

[0023] obtaining the average illumination intensity of the illumination area of each of the cigar leaves in a preset period, and substituting the illumination proportion of each of the cigar leaves and the average illumination intensity in the preset period into Formula II to determine the comprehensive illumination score of the curing area, the Formula II being as follows:

[0024]

[0025] wherein L is the comprehensive illumination score of the curing area, n is the number of the cigar leaves, Ri is the illumination proportion of the cigar leaves, Ii is the average illumination intensity of the cigar leaves in a preset period, Imax is the preset illumination intensity, W R and W I are weight coefficients, and the sum of W R and W I is 1;

[0026] determining whether to adjust the early warning score according to the relationship between the comprehensive illumination score L of the curing area and a preset comprehensive illumination score;

[0027] when the comprehensive illumination score L is greater than or equal to the preset comprehensive illumination score, it is determined that the early warning score is not adjusted;

[0028] When the comprehensive illumination score L is less than the preset comprehensive illumination score, an adjustment coefficient is determined based on the difference between the comprehensive illumination score L and the preset comprehensive illumination score, and the warning score is adjusted according to the adjustment coefficient.

[0029] Furthermore, when determining the adjustment coefficient based on the difference between the comprehensive illumination score L and the preset comprehensive illumination score, the following steps are included:

[0030] The adjustment coefficient is determined based on the comparison between the light score difference and the pre-configured first preset light score difference and second preset light score difference.

[0031] When the difference in illumination score is less than or equal to the first preset difference in illumination score, the adjustment coefficient is determined to be X3;

[0032] When the difference in illumination score is greater than the first preset difference in illumination score, and the difference in illumination score is less than or equal to the second preset difference in illumination score, then the adjustment coefficient is determined to be X2.

[0033] When the difference in illumination score is greater than the second preset difference in illumination score, the adjustment coefficient is determined to be X1;

[0034] Wherein, the first preset illumination score difference is less than the second preset illumination score difference, X1 < X2 < X3 < 1.

[0035] Furthermore, when the adjustment coefficient is determined to be Xi, i = 1, 2, 3, it includes:

[0036] The real-time ambient temperature of the drying area is obtained, and based on the relationship between the real-time ambient temperature and the pre-configured preset temperature, it is determined whether to correct the adjustment coefficient Xi.

[0037] When the real-time ambient temperature is greater than or equal to the preset temperature, it is determined that the adjustment coefficient Xi will not be corrected.

[0038] When the real-time ambient temperature is lower than the preset temperature, a correction coefficient is determined based on the temperature difference between the real-time ambient temperature and the preset temperature, and the adjustment coefficient Xi is corrected based on the correction coefficient.

[0039] Furthermore, when determining the correction coefficient based on the temperature difference between the real-time ambient temperature and the preset temperature, the following steps are included:

[0040] The correction coefficient is determined based on the relationship between the temperature difference and a pre-configured first preset temperature difference and a second preset temperature difference.

[0041] when the temperature difference is greater than the first preset temperature difference and less than or equal to the second preset temperature difference, the correction coefficient is determined as C2;

[0042] when the temperature difference is greater than the first preset temperature difference and less than or equal to the second preset temperature difference, the correction coefficient is determined as C2;

[0043] when the temperature difference is greater than the second preset temperature difference, the correction coefficient is determined as C1;

[0044] wherein the first preset temperature difference is less than the second preset temperature difference, and C1

[0045] Further, when the correction coefficient is determined as Ci, i = 1, 2, 3, comprising:

[0046] obtaining the real-time ambient humidity of the airing area, and determining whether to correct the correction coefficient Ci according to the relationship between the real-time ambient humidity and a preset humidity configured in advance;

[0047] when the real-time ambient humidity is less than the preset humidity, it is determined that the correction coefficient Ci is not corrected;

[0048] when the real-time ambient humidity is greater than or equal to the preset humidity, a correction coefficient is determined according to the humidity difference between the real-time ambient humidity and the preset humidity, and the correction coefficient Ci is corrected according to the correction coefficient.

[0049] Further, when the correction coefficient is determined according to the humidity difference between the real-time ambient humidity and the preset humidity, comprising:

[0050] determining the correction coefficient according to the relationship between the humidity difference and the first preset humidity difference and the second preset humidity difference configured in advance;

[0051] when the humidity difference is less than or equal to the first preset humidity difference, the correction coefficient is determined as B3;

[0052] when the humidity difference is greater than the first preset humidity difference and less than or equal to the second preset humidity difference, the correction coefficient is determined as B2;

[0053] when the humidity difference is greater than the second preset humidity difference, the correction coefficient is determined as B1;

[0054] wherein the first preset humidity difference is less than the second preset humidity difference, and B1

[0055] The computer readable storage medium further stores program instructions, which, when executed, implement the method for intelligently monitoring puffy green spots in cigar leaf curing.

[0056] The computer readable storage medium further stores program instructions, which, when executed, implement the method for intelligently monitoring puffy green spots in cigar leaf curing.

[0057] Compared with the prior art, the method has the beneficial effects that: by constructing a puffy green spot feature set based on image recognition technology, the method realizes rapid positioning and hierarchical management of diseased leaves. By obtaining and analyzing the area and number of puffy green spots of the leaves, the density of the green spots is calculated, and the disease level of the diseased leaves is automatically determined. Hierarchical management enables the system to clearly determine the distribution of leaves of different disease levels, providing reliable data support for subsequent process adjustment. The division of disease levels also facilitates intelligent screening and hierarchical early warning, reducing the detection difficulty and misjudgment risk caused by unobvious green spot features. In addition, by introducing environmental parameters such as illumination, ambient temperature and humidity, the method more comprehensively analyzes the green spot early warning score of the curing area. Through real-time acquisition and dynamic adjustment, the addition of these environmental parameters makes the early warning score more accurate. Compared with a static scoring system, a dynamic scoring system adjusts the early warning level according to real-time environmental conditions, thereby improving the accuracy of early warning, helping management personnel to identify and prevent potential curing problems earlier, and optimizing the decision-making process of the curing process. Finally, by setting first and second preset early warning score standards, the early warning level is determined according to the difference between the score and the actual situation, further improving the practicality and response speed of the system. The early warning level classification mechanism can prompt and guide the operator to take appropriate measures according to different levels of alarm, realizing an integrated management process from green spot detection to environmental parameter adjustment and early warning response, and providing a more efficient, intelligent and reliable management means for cigar leaf curing. BRIEF DESCRIPTION OF DRAWINGS

[0058] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are for purposes of illustration only and are not considered a limitation of the present application. Moreover, like reference numerals are used to designate identical components throughout the specification and drawings. In the drawings:

[0059] Figure 1 A flowchart of a method for intelligently monitoring puffy green spots in cigar leaf curing according to an embodiment of the present application. DETAILED DESCRIPTION

[0060] Exemplary embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the present disclosure to those skilled in the art. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0061] As shown in Figure 1 In some embodiments of the present application, the present embodiments provide an intelligent monitoring method for bubble-shaped green spots in cigar leaf curing, comprising:

[0062] Step S100, acquiring image information of bubble-shaped green spots in each cigar leaf curing, and establishing a bubble-shaped green spot feature set according to the bubble-shaped green spot features in each image information.

[0063] Step S200, acquiring surface images of each cigar leaf in the curing area, and matching the bubble-shaped green spot features between the surface image features and the bubble-shaped green spot feature set.

[0064] Specifically, the matching between the bubble-shaped green spot features between the surface image features and the bubble-shaped green spot feature set comprises: when the surface image features match the bubble-shaped green spot features, it is determined that the cigar leaf corresponding to the surface image features is a sick leaf, and the area and number of bubble-shaped green spot features in the sick leaf are acquired, and the bubble-shaped green spot density of the sick leaf is determined according to the area and number of bubble-shaped green spot features and the area of the sick leaf. The sick level of the sick leaf is determined according to the bubble-shaped green spot density, wherein the sick level is first sick level, second sick level and third sick level in turn.

[0065] It can be understood that the surface images of each piece of tobacco leaf in the curing area are obtained by a high-resolution camera. These images not only contain the overall appearance of the tobacco leaf, but also capture the subtle changes on its surface in detail. This process is the first step of intelligent monitoring, laying the foundation for subsequent image analysis. Next, by using image recognition algorithms, especially convolutional neural networks (CNN) in deep learning, the features of the obtained tobacco leaf surface images are extracted and matched. By comparing with the pre-established bubble-shaped blight feature set, it can quickly determine whether there are blights in the surface image. The key to this process lies in the training of the algorithm, and the model needs to be trained on a large number of labeled image data to improve its recognition accuracy of blight features. This intelligent matching technology effectively solves the misjudgment and omission problems caused by insufficient experience in manual detection, thereby significantly improving the reliability and efficiency of detection. Once the bubble-shaped blight in the tobacco leaf is confirmed, the characteristics of these blights, including their area and number, are further analyzed. By calculating the ratio of the area of the blight to the area of the entire diseased tobacco leaf, the blight density, an important indicator, can be obtained. Blight density reflects the severity of the disease and is a key parameter for evaluating the health of tobacco leaves. The higher the density, the more serious the disease of the tobacco leaf, and the manager can quickly take appropriate measures based on this data to ensure the smooth progress of the curing process. Finally, according to the calculated blight density, the diseased tobacco leaves are classified into first, second, and third disease levels. This classification management not only facilitates the classification of tobacco leaf quality, but also provides a clear disease risk assessment for managers. By implementing different treatment strategies for tobacco leaves of different disease levels, the impact of disease on the entire curing process can be more effectively reduced. In addition, the determination of disease levels also provides data support for the subsequent early warning mechanism, making the overall quality management more scientific and accurate.

[0066] Step S300, according to the number of diseased tobacco leaves in the curing area and the disease level of each diseased tobacco leaf, determine the early warning score of the curing area.

[0067] Specifically, when determining the early warning score of the curing area according to the number of diseased tobacco leaves in the curing area and the disease level of each diseased tobacco leaf, it includes: obtaining the number of first disease level diseased tobacco leaves, the number of second disease level diseased tobacco leaves and the number of third disease level diseased tobacco leaves, and substituting the number of first disease level diseased tobacco leaves, the number of second disease level diseased tobacco leaves and the number of third disease level diseased tobacco leaves into Formula I to determine the early warning score of the curing area, Formula I is as follows: P = z1 × Q + z2 × K + z3 × J. Wherein, P is the early warning score of the curing area, Q is the number of first disease level diseased tobacco leaves, K is the number of second disease level diseased tobacco leaves, J is the number of third disease level diseased tobacco leaves, z1-z3 are weight coefficients, and the sum of z1-z3 is 1.

[0068] It can be understood that by quantitatively analyzing the number of tobacco leaves of different disease levels, the manager can effectively evaluate the overall health status of the curing area. Specifically, the model uses the formula P = z1 x Q + z2 x K + z3 x J, where P represents the early warning score of the curing area, which can reflect the disease risk of the tobacco leaves in the area to some extent. The calculation of this score takes into account the number of tobacco leaves of different disease levels, represented by Q, K and J for the first, second and third disease levels, respectively. In this way, the manager can clearly understand the role and influence of tobacco leaves of each disease level in the overall assessment. Secondly, in order to ensure the scientificity and rationality of the early warning score, the model introduces weight coefficients z1, z2 and z3. The setting of these weight coefficients is not only based on the relative influence of each disease level on the quality of tobacco leaves, but also can be dynamically adjusted according to actual conditions. For example, in a particular climate condition or production link, a certain disease level may have a more significant impact on the overall quality, at which time the manager can adjust the weight of that level accordingly to improve the prediction accuracy and adaptability of the model. In summary, the flexibility of the weight makes the model more practical and better meets the actual production needs. In addition, the early warning score P obtained by calculation not only provides a quantitative risk assessment tool for managers, but also helps them make scientific management decisions in actual operation. When the P value is low, it means that the health status of the tobacco leaves in the curing area is good, and the manager can continue to maintain the existing production process; when the P value rises to a certain threshold, the manager needs to pay attention and may need to adjust the curing conditions accordingly to prevent the spread of disease. For example, if the number of tobacco leaves of the second disease level increases significantly, the manager can consider reducing humidity or increasing ventilation to improve the curing environment and reduce the risk of damage to tobacco leaves. Finally, when the manager monitors changes in the early warning score of the curing area, he can quickly develop response measures through a pre-set response mechanism. By combining the actual situation of the curing area with the evaluation results, the manager can more effectively optimize the production process and ensure the stability of the quality of the final product. This forward-looking management approach not only reduces production risks, but also improves overall work efficiency, helping the development of intelligent and fine cigar production.

[0069] Step S400, the light intensity of each cigar tobacco leaf in the curing area, the environmental temperature and humidity of the curing area are obtained, and the early warning score is adjusted according to the light intensity of each cigar tobacco leaf, the environmental temperature and humidity of the curing area.

[0070] Specifically, when adjusting the early warning score according to the light intensity of each cigar leaf, the ambient temperature and the ambient humidity of the curing area, the following steps are included: obtaining the light area of each cigar leaf in a preset period, and determining the light proportion of each cigar leaf according to the light area and the area of the cigar leaf; obtaining the average light intensity of the light area in the preset period, and substituting the light proportion of each cigar leaf and the average light intensity in the preset period into Formula II to determine the comprehensive light score of the curing area, Formula II is as follows:

[0071]

[0072] wherein, L is the comprehensive light score of the curing area, n is the number of cigar leaves, R i is the light proportion of the cigar leaf, I i is the average light intensity of the light area of the cigar leaf in the preset period, Imax is the preset light intensity, W R and W I are weight coefficients, and the sum of W R and W I is 1. According to the relationship between the comprehensive light score L of the curing area and the preset comprehensive light score, it is determined whether to adjust the early warning score. When the comprehensive light score L is greater than or equal to the preset comprehensive light score, it is determined that the early warning score is not adjusted. When the comprehensive light score L is less than the preset comprehensive light score, the adjustment coefficient is determined according to the light score difference between the comprehensive light score L and the preset comprehensive light score, and the early warning score is adjusted according to the adjustment coefficient.

[0073] Specifically, when the adjustment coefficient is determined according to the light score difference between the comprehensive light score L and the preset comprehensive light score, the following steps are included: comparing the light score difference with the first preset light score difference and the second preset light score difference configured in advance, and determining the adjustment coefficient according to the comparison result: when the light score difference is less than or equal to the first preset light score difference, the adjustment coefficient is X3. When the light score difference is greater than the first preset light score difference and less than or equal to the second preset light score difference, the adjustment coefficient is X2. When the light score difference is greater than the second preset light score difference, the adjustment coefficient is X1. Wherein, the first preset light score difference is less than the second preset light score difference, X1

[0074] It can be understood that by obtaining the illumination area of each cigar leaf and calculating the illumination ratio with the total area, the degree of light received by each leaf in a specific time period is reflected. The calculation of the illumination ratio is an important step, which can intuitively show the relative intensity of the light received by the leaf. The core of this process is how to accurately measure and calculate the light conditions for subsequent scoring analysis. In this way, the actual light of each leaf can be obtained, thereby providing an accurate data basis for subsequent comprehensive light scoring. Then, considering the illumination ratio of each leaf and the average light intensity, the comprehensive light score L of the curing area is calculated by using formula II. This score calculation integrates the light information and environmental conditions of multiple leaves, ensuring that the overall impact of light on the leaf is fully reflected. In this process, the average light intensity provides a benchmark for each leaf to be compared with other leaves. In addition, appropriate weight coefficients W R and W I The influence of illumination ratio and light intensity can be adjusted according to actual production needs to further improve the accuracy and practicality of the score. Further, the comprehensive light score L will be compared with the preset standard light score to determine whether the current warning score needs to be adjusted. This dynamic feedback mechanism enables the monitoring system to respond to environmental changes in real time and adjust production strategies in a timely manner. When the comprehensive light score is lower than the preset value, it means that the curing area may have insufficient light, which can have a negative impact on the quality of cigar leaves. Therefore, by setting reasonable preset standards, producers can be alerted to take appropriate measures to ensure the quality of the leaves is not compromised. If the comprehensive light score is lower than the preset value, the adjustment coefficient is calculated according to the difference between the two. This adjustment coefficient is calculated by comparing it with the predefined light score difference threshold to determine the specific impact on the warning score. This detailed adjustment mechanism enables the warning score to be dynamically adjusted according to the actual light conditions, thereby achieving more accurate risk management.

[0075] Specifically, when the adjustment coefficient Xi is determined, i = 1, 2, 3, it includes: obtaining the real-time environmental temperature of the curing area, and determining whether to correct the adjustment coefficient Xi according to the relationship between the real-time environmental temperature and the preset temperature: when the real-time environmental temperature is greater than or equal to the preset temperature, it is determined that the adjustment coefficient Xi is not corrected. When the real-time environmental temperature is less than the preset temperature, the correction coefficient is determined according to the temperature difference between the real-time environmental temperature and the preset temperature, and the adjustment coefficient Xi is corrected according to the correction coefficient.

[0076] Specifically, when determining the correction coefficient according to the temperature difference between the real-time ambient temperature and the preset temperature, the method comprises: determining the correction coefficient according to the relationship between the temperature difference and the first preset temperature difference and the second preset temperature difference. When the temperature difference is less than or equal to the first preset temperature difference, the correction coefficient is determined as C3. When the temperature difference is greater than the first preset temperature difference and less than or equal to the second preset temperature difference, the correction coefficient is determined as C2. When the temperature difference is greater than the second preset temperature difference, the correction coefficient is determined as C1. Wherein, the first preset temperature difference is less than the second preset temperature difference, and C1

[0077] Specifically, when the correction coefficient is determined as Ci, i = 1, 2, 3, the method comprises: obtaining the real-time ambient humidity of the airing area, and determining whether to correct the correction coefficient C i according to the relationship between the real-time ambient humidity and the preset humidity. When the real-time ambient humidity is less than the preset humidity, it is determined that the correction coefficient C i is not corrected. When the real-time ambient humidity is greater than or equal to the preset humidity, the correction coefficient is determined according to the humidity difference between the real-time ambient humidity and the preset humidity, and the correction coefficient C i is corrected according to the correction coefficient.

[0078] Specifically, when determining the correction coefficient according to the humidity difference between the real-time ambient humidity and the preset humidity, the method comprises: determining the correction coefficient according to the relationship between the humidity difference and the first preset humidity difference and the second preset humidity difference. When the humidity difference is less than or equal to the first preset humidity difference, the correction coefficient is determined as B3. When the humidity difference is greater than the first preset humidity difference and less than or equal to the second preset humidity difference, the correction coefficient is determined as B2. When the humidity difference is greater than the second preset humidity difference, the correction coefficient is determined as B1. Wherein, the first preset humidity difference is less than the second preset humidity difference, and B1

[0079] It can be understood that during the curing process of cigar leaves, environmental conditions such as temperature and humidity have a significant impact on the quality of the leaves. Therefore, real-time monitoring of these factors and making appropriate adjustments is key to ensuring product quality. Specifically, by obtaining the environmental temperature of the curing area in real time, it can be determined in real time whether the current temperature is within the ideal range. When the real-time environmental temperature is higher than or equal to the preset temperature, it indicates that the curing conditions are good, so there is no need to modify the adjustment coefficient. However, if the real-time temperature is lower than the preset temperature, the temperature difference will be calculated, and the correction coefficient will be determined based on this difference. This mechanism ensures that adjustments can be made proactively in low-temperature conditions to avoid the negative effects of excessively low temperatures on the drying effect of the leaves. At the same time, during the determination of the correction coefficient C i, the monitoring of environmental humidity also plays a crucial role. Humidity has a direct impact on the drying speed of the leaves and their final quality. When the real-time environmental humidity is lower than the preset humidity, it is determined that the environmental conditions are good, so no humidity correction is made. When the humidity exceeds the preset value, the correction coefficient is calculated using the humidity difference to further optimize the previous correction coefficient. The implementation of this process ensures that in high-humidity environments, operational parameters can be adjusted in a timely manner to address potential moisture damage to the leaves. Finally, by combining the monitoring of temperature and humidity, this section establishes a multi-level intelligent monitoring and adjustment mechanism. This mechanism not only allows for real-time responses to environmental changes to ensure optimal curing conditions for the leaves, but also improves the producer's ability to anticipate potential problems. Producers can respond quickly based on real-time data, effectively reducing production losses due to environmental factors. In addition, this dynamic adjustment capability helps reduce the frequency of manual intervention, reducing the risks and labor intensity associated with routine inspections, making the entire production process safer and more efficient.

[0080] Step S500, obtain the adjusted early warning score, and determine the early warning level of the curing area according to the relationship between the adjusted early warning score and the first preset early warning score and the second preset early warning score.

[0081] Specifically, when the adjusted early warning score is less than the first preset early warning score, the early warning level of the curing area is determined to be a low-risk level. When the adjusted early warning score is greater than or equal to the first preset early warning score and less than the second preset early warning score, the early warning level of the curing area is determined to be a medium-risk level. When the adjusted early warning score is greater than or equal to the second preset early warning score, the early warning level of the curing area is determined to be a high-risk level.

[0082] It can be understood that by collecting a variety of data related to the quality of tobacco leaves, including the density of green spots, environmental light intensity, temperature and humidity, etc. These factors are considered important indicators that affect the quality of cigar tobacco leaves. By analyzing these data comprehensively, an adjusted early warning score is generated. This score reflects the overall health status of the current curing area, providing a quantitative basis for subsequent risk assessment. Next, by comparing the adjusted early warning score with two pre-set key thresholds. These two pre-set scores represent different risk levels, corresponding to low-risk and high-risk areas respectively. By checking whether the adjusted score is lower than the first pre-set threshold. If so, the area is determined to be a low-risk level, indicating that the health of the tobacco leaves is good, and the manager can continue to observe and maintain the existing curing process without additional intervention. Such a design not only reduces unnecessary operations, but also effectively reduces resource waste. If the adjusted early warning score is between the first and second thresholds, the area is determined to be a medium-risk level. This classification means that the tobacco leaves may have some health problems, and the manager should pay attention to it and consider adjusting the curing conditions, such as controlling humidity, improving ventilation or increasing light, etc. Through timely intervention measures, the risk of disease spread can be effectively reduced, thereby ensuring the quality of the final product. Finally, when the adjusted early warning score is higher than the second pre-set threshold, the area is marked as a high-risk level. This indicates that the health of the tobacco leaves has deteriorated seriously, and there may be significant green spots or other diseases. At this time, the manager needs to take immediate action, including strengthening the monitoring of the curing process, conducting a comprehensive inspection, and even possibly isolating the affected tobacco leaves for processing to prevent the spread of disease. Through such a high-risk warning mechanism, managers can identify and respond to potential production problems in a timely manner, ensuring the safety and stability of the entire cigar production process.

[0083] In the above embodiment, by constructing a set of bubble-like green spot features based on image recognition technology, the rapid positioning and hierarchical management of sick tobacco leaves are realized. By obtaining and analyzing the bubble-like green spot feature area and quantity of tobacco leaves, the density of green spots is calculated, and the disease level of sick tobacco leaves is automatically determined. Hierarchical management enables the system to clearly determine the distribution of tobacco leaves of different disease levels, providing reliable data support for subsequent process adjustment. The division of disease levels also facilitates intelligent screening and hierarchical early warning, reducing the detection difficulty and misjudgment risk caused by unclear green spot features. In addition, by introducing environmental parameters such as illumination, ambient temperature and humidity, the green spot early warning score of the curing area is more comprehensively analyzed. Through real-time collection and dynamic adjustment, the addition of these environmental parameters makes the early warning score more accurate. Compared with the static scoring system, the dynamic scoring system adjusts the early warning level according to the real-time environmental conditions, thereby improving the accuracy of early warning, helping management personnel to identify and prevent potential curing problems earlier, and optimizing the decision-making process of the curing process. Finally, by setting the first and second preset early warning score standards, the early warning level is determined according to the difference between the score and the actual situation, further improving the practicality and response speed of the system. The early warning level classification mechanism can prompt and guide the operating personnel to take appropriate measures according to different levels of alarm, realizing an integrated management process from green spot detection to environmental parameter adjustment and early warning response, and providing a more efficient, intelligent and reliable management means for cigar tobacco curing.

[0084] In another preferred mode based on the above embodiment, the present embodiment provides a computer-readable storage medium, wherein the computer-readable storage medium stores program instructions, and the program instructions, when executed, are used to execute a method for intelligent monitoring of bubble-like green spots in cigar tobacco curing.

[0085] In another preferred mode based on the above embodiment, the present embodiment also provides an intelligent monitoring system for bubble-like green spots in cigar tobacco curing, wherein the intelligent monitoring system for bubble-like green spots in cigar tobacco curing includes the above computer-readable storage medium.

[0086] Those skilled in the art will appreciate that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can be in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can be in the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0087] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks. Figure 1 one or more flow or blocks.

[0088] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flow or blocks. Figure 1 one or more flow or blocks.

[0089] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks. Figure 1 one or more flow or blocks.

[0090] Finally, it should be noted that the above-mentioned embodiments are merely used to illustrate the technical solutions of the present application, but not limit the technical solutions of the present application. Although the present application has been described in detail with reference to the above-mentioned embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalent replaced without departing from the spirit and scope of the present application, and any modification or equivalent replacement should be covered in the protection scope of the present application.

Claims

1. A method for intelligent monitoring of bubble-like green spots in the curing of cigar tobacco leaves, characterized by, The method comprises the following steps: acquiring image information of bubble-shaped green spots in each cigar leaf during curing, and establishing a bubble-shaped green spot feature set according to the bubble-shaped green spot features in each image information; acquiring surface images of each cigar leaf in the curing area, and matching the bubble-shaped green spot features between the surface image features and the bubble-shaped green spot feature set, wherein: when the surface image features match the bubble-shaped green spot features, it is determined that the cigar leaf corresponding to the surface image features is a sick leaf, and the area and number of the bubble-shaped green spot features in the sick leaf are acquired, and the bubble-shaped green spot density of the sick leaf is determined according to the area and number of the bubble-shaped green spot features and the area of the sick leaf; determining the sick level of the sick leaf according to the bubble-shaped green spot density, wherein the sick levels are sequentially a first sick level, a second sick level and a third sick level; determining a warning score of the curing area according to the number of sick leaves in the curing area and the sick level of each sick leaf; acquiring the illumination of each cigar leaf, the environmental temperature and the environmental humidity of the curing area, and adjusting the warning score according to the illumination of each cigar leaf, the environmental temperature and the environmental humidity of the curing area; acquiring the adjusted warning score, and determining a warning level of the curing area according to the relationship between the adjusted warning score and pre-configured first and second preset warning scores, wherein: when the adjusted warning score is less than the first preset warning score, it is determined that the warning level of the curing area is a low-risk level; when the adjusted warning score is greater than or equal to the first preset warning score and less than the second preset warning score, it is determined that the warning level of the curing area is a medium-risk level; when the adjusted warning score is greater than or equal to the second preset warning score, it is determined that the warning level of the curing area is a high-risk level.

2. The method for intelligent monitoring of blister mottle in cigar leaf curing according to claim 1, characterized in that, When determining the warning score of the curing area according to the number of sick leaves in the curing area and the sick level of each sick leaf, the method comprises the following steps: acquiring the number of sick leaves of the first sick level, the number of sick leaves of the second sick level and the number of sick leaves of the third sick level, and substituting the number of sick leaves of the first sick level, the number of sick leaves of the second sick level and the number of sick leaves of the third sick level into Formula I to determine the warning score of the curing area, wherein the Formula I is as follows: P=z1×Q+z2×K+z3×J; wherein P is the warning score of the curing area, Q is the number of sick leaves of the first sick level, K is the number of sick leaves of the second sick level, J is the number of sick leaves of the third sick level, z1-z3 are weight coefficients, and the sum of z1-z3 is 1.

3. The method for intelligent monitoring of blister speck in cigar leaf curing according to claim 1, wherein, When adjusting the warning score according to the illumination of each cigar leaf, the environmental temperature and the environmental humidity of the curing area, the method comprises the following steps: acquire an illumination area of each of the cigar leaves within a preset period of time, and determine an illumination proportion of each of the cigar leaves according to the illumination area and an area of the cigar leaf; An average light intensity of a light area in a preset period of the cigar leaf is obtained, and the light proportion of each of the cigar leaves and the average light intensity in the preset period are substituted into Formula II to determine a comprehensive light evaluation score of the curing area, the Formula II being as follows: ; Wherein, L is the comprehensive light exposure score of the curing area, n is the number of the cigar leaves, Ri is the light exposure proportion of the cigar leaves, Ii is the average light intensity of the cigar leaves in a preset period, Imax is a preset light intensity, W R and W I are weight coefficients, and the sum of W R and W I is 1. determine whether to adjust the early warning score according to a relationship between the comprehensive illumination score L of the curing area and a preset comprehensive illumination score; when the comprehensive illumination score L is greater than or equal to the preset comprehensive illumination score, it is determined that the early warning score is not adjusted; when the comprehensive illumination score L is less than the preset comprehensive illumination score, an adjustment coefficient is determined according to an illumination score difference between the comprehensive illumination score L and the preset comprehensive illumination score, and the early warning score is adjusted according to the adjustment coefficient.

4. The method for intelligent monitoring of blister mottle in cigar leaf curing according to claim 3, characterized in that, when the adjustment coefficient is determined according to the illumination score difference between the comprehensive illumination score L and the preset comprehensive illumination score, comprising: comparing the illumination score difference with a first preset illumination score difference and a second preset illumination score difference configured in advance, and determining the adjustment coefficient according to the comparison result; when the illumination score difference is less than or equal to the first preset illumination score difference, the adjustment coefficient is determined as X3; when the illumination score difference is greater than the first preset illumination score difference and less than or equal to the second preset illumination score difference, the adjustment coefficient is determined as X2; when the illumination score difference is greater than the second preset illumination score difference, the adjustment coefficient is determined as X1; wherein the first preset illumination score difference is less than the second preset illumination score difference, and X1X2X3<1.

5. The method for intelligent monitoring of blister speck in tobacco curing as claimed in claim 4, wherein, when the adjustment coefficient is determined as Xi, i=1, 2, 3, comprising: acquiring a real-time environment temperature of the curing area, and determining whether to correct the adjustment coefficient Xi according to a relationship between the real-time environment temperature and a preset temperature configured in advance; when the real-time environment temperature is greater than or equal to the preset temperature, it is determined that the adjustment coefficient Xi is not corrected; when the real-time environment temperature is less than the preset temperature, a correction coefficient is determined according to a temperature difference between the real-time environment temperature and the preset temperature, and the adjustment coefficient Xi is corrected according to the correction coefficient.

6. The method for intelligent monitoring of blister speck in tobacco curing as claimed in claim 5, wherein, when the correction coefficient is determined according to the temperature difference between the real-time environment temperature and the preset temperature, comprising: determining the correction coefficient according to a relationship between the temperature difference and a first preset temperature difference and a second preset temperature difference configured in advance; when the temperature difference is less than or equal to the first preset temperature difference, the correction coefficient is determined as C3; when the temperature difference is greater than the first preset temperature difference and less than or equal to the second preset temperature difference, the correction coefficient is determined as C2; when the temperature difference is greater than the second preset temperature difference, the correction coefficient is determined as C1; wherein the first preset temperature difference is less than the second preset temperature difference, and C1 7. The method for intelligent monitoring of blister speck in tobacco curing as claimed in claim 6, wherein, when the correction coefficient is determined as Ci, i=1, 2, 3, comprising: acquiring a real-time ambient humidity of the airing area, and determining whether to correct the correction coefficient Ci according to a relationship between the real-time ambient humidity and a preset humidity configured in advance; when the real-time ambient humidity is less than the preset humidity, it is determined that the correction coefficient Ci is not corrected; when the real-time ambient humidity is greater than or equal to the preset humidity, a correction coefficient is determined according to a humidity difference between the real-time ambient humidity and the preset humidity, and the correction coefficient Ci is corrected according to the correction coefficient.

8. The method for intelligent monitoring of blister mottle in cigar leaf curing according to claim 7, wherein, when the correction coefficient is determined according to the humidity difference between the real-time ambient humidity and the preset humidity, comprising: the correction coefficient is determined according to a relationship between the humidity difference and first and second preset humidity differences configured in advance; when the humidity difference is less than or equal to the first preset humidity difference, the correction coefficient is B3; when the humidity difference is greater than the first preset humidity difference and less than or equal to the second preset humidity difference, the correction coefficient is B2; when the humidity difference is greater than the second preset humidity difference, the correction coefficient is B1; wherein the first preset humidity difference is less than the second preset humidity difference, and B1 9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores program instructions, and the program instructions run to execute the method of claim 1-8.

10. A system for intelligent monitoring of blister mottling in cigar leaf curing, characterized by, The computer readable storage medium of claim 9. The computer readable storage medium of claim 9.

Images