Macadamia nut maturity evaluation system

Abstract

The invention discloses a macadamia nut maturity evaluation system, and relates to the technical field of maturity evaluation, the evaluation system comprises a monitoring trigger module, an image processing module, a spectral analysis module and a detection adjustment module; the technical key points are as follows: refined evaluation and dynamic adjustment of macadamia nut maturity are realized, flintiness analysis is performed on fruits which do not reach the standard in a fuzzy manner, a dynamic adjustment calculation model is constructed in combination with a hardness value, a standard value and an adjustment data set, a corrected evaluation threshold value is generated, and the macadamia nut maturity is evaluated and dynamically adjusted. The problem that the evaluation result is inaccurate due to a fixed threshold value in a traditional evaluation method is effectively solved; two adjustment items including the hardness abnormal proportion and the average hardness deviation are introduced, the hardness condition of the fruits which do not reach the standard is comprehensively considered, fine adjustment of the evaluation threshold value is achieved, and the accuracy and flexibility of evaluation are improved; meanwhile, by dynamically adjusting the evaluation threshold, the actual maturity condition of the fruits can be reflected more accurately, and a scientific basis is provided for agricultural production.

Description

Technical Field

[0001] The present invention relates to the technical field of maturity assessment, and in particular to a macadamia nut maturity assessment system. Background Art

[0002] The maturity of macadamia nuts is mainly assessed by appearance and physical and chemical indicators. In terms of appearance, the surface color of mature macadamia nuts is dark brown or reddish brown, the shell is relatively hard and will tilt, and the fruit will fall naturally. In terms of physical and chemical indicators, the maturity can be determined by testing the oil content of the kernel. Usually, the oil content of mature kernels is extremely high, reaching about 72%. In actual operation, the kernel of the fresh fruit can be peeled and cracked, and then placed in water to observe the floating and sinking of the kernel. If the kernel floats up completely, it means that the fruit is ripe. If it sinks, it means that the sugar content in the kernel is high, the oil has not been completely converted, and the fruit is not yet ripe. The combination of appearance observation and physical and chemical indicator testing can accurately assess the maturity of macadamia nuts and ensure that the quality of the harvested fruit is excellent.

[0003] In the existing process of assessing the maturity of nuts, it is necessary to select one or more monitoring points and use the results of the monitoring points to reflect the entire nut planting area. Traditional agricultural monitoring has problems such as large assessment errors and waste of resources due to uneven distribution of monitoring points and inaccurate monitoring timing. When assessing the maturity of nuts, it is determined by manual contact. If the operation is improper, it will not only cause the spread of pests and diseases, but also make it difficult to achieve rapid and accurate assessment, and the errors in the assessment results are also difficult to avoid. Summary of the invention

[0004] 1. Technical issues to be solved

[0005] In view of the shortcomings of the prior art, the present invention provides a macadamia nut maturity assessment system, which solves the problems raised in the background technology.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0008] A macadamia nut maturity assessment system, the system comprising:

[0009] The monitoring trigger module evenly configures monitoring points according to the area of ​​the target park, obtains the real-time density of macadamia nuts at each monitoring point in real time, and monitors the current monitoring point to obtain the time point when the real-time density drops from the maximum value to the predetermined interval calibration value during the maturity estimation period. The maturity assessment mechanism is triggered at this time point;

[0010] The image processing module executes the maturity assessment mechanism, randomly obtains the image data of M fallen macadamia nuts at the corresponding monitoring point, uses edge detection and texture analysis technology to obtain the comparison data set of each macadamia nut, builds a rule engine, compares the data in the comparison data set with the corresponding defined threshold, and calibrates and calculates the maturity level value at the corresponding monitoring point based on the comparison result;

[0011] The spectral analysis module builds a weighted calculation model based on the maturity grade value and the spectral analysis results to generate a maturity estimate for the target park, and compares the preset assessment threshold of the maturity estimate to determine whether the maturity of the macadamia nuts in the target park meets the fuzzy standard;

[0012] If the fuzzy meets the standard, the result will be output;

[0013] If the fuzziness does not meet the target, the analysis adjustment strategy is triggered;

[0014] The detection and adjustment module executes the analysis and adjustment strategy, extracts the macadamia nuts in the target park whose maturity does not meet the fuzzy standard and the number of fruits S, performs hardness analysis and measurement on the fruits that do not meet the fuzzy standard, obtains the hardness value of each fruit, and compares each hardness value with the standard value to obtain the proportion of fruits with hardness values ​​exceeding the standard value. Combined with the collected adjustment data set, a dynamic adjustment calculation model is constructed to generate a revised evaluation threshold, which is compared with the maturity estimate for a second time, and whether the maturity of the macadamia nuts in the target park meets the standard is determined based on the comparison results.

[0015] Furthermore, the ratio between the monitoring points and the land area is 1:30, and the number of monitoring points is set as follows: if the land area is less than 30, the monitoring points are configured at the center of the target park; if the land area is not an integer multiple of 30, the number of monitoring points is: the current land area is rounded up to the integer of 30 multiples.

[0016] Further, the preset interval calibration value represents: the real-time density maximum value - 0.3% of the real-time density maximum value, and 0.3% of the real-time density maximum value represents the preset interval value.

[0017] Furthermore, the comparison data set includes the number of cracks and texture contrast; wherein the number of cracks is identified by the Canny edge detection algorithm, and the texture contrast is calculated by GLCM.

[0018] Furthermore, the data in the comparison data set were compared with the corresponding definition thresholds, and the comparison results were as follows: for each fallen macadamia nut, if the number of cracks exceeded the corresponding definition threshold and the texture contrast was lower than the corresponding definition threshold, the maturity grade of the corresponding macadamia nut was calibrated as level two; if the number of cracks was lower than the corresponding definition threshold and the texture contrast exceeded the corresponding definition threshold, the maturity grade of the corresponding macadamia nut was calibrated as level one.

[0019] Furthermore, the process of obtaining the maturity level value at the corresponding monitoring point is as follows:

[0020] Count the maturity level of each of the M macadamia nuts;

[0021] The average calculation is performed, and the value obtained is the maturity level value at the corresponding monitoring point;

[0022] The value of M is at least 3 and is a positive integer.

[0023] Furthermore, the process of spectral analysis is: the fatty acid content of M fallen macadamia nuts is analyzed by near infrared spectrometer, so the fatty acid content of each macadamia nut is the result of spectral analysis.

[0024] Furthermore, the process of constructing a weighted calculation model is as follows:

[0025] The fatty acid content of M macadamia nuts was depolarized;

[0026] Perform mean calculation to obtain the mean value of fatty acid content;

[0027] The mean value of fatty acid content and maturity grade value were dimensionless and then weighted calculated. The formula is:

[0028] Gy=F1*Zs avg +F2*Cd;

[0029] In the formula, Gy represents the maturity estimation, F1 and F2 are weight coefficients, and F1+F2=1, Zs avg represents the mean fatty acid content, and Cd represents the maturity grade value.

[0030] Furthermore, the preset assessment thresholds of maturity valuation are compared, and the comparison process is as follows:

[0031] When the maturity valuation exceeds the assessment threshold, the fuzzy standard is determined to be met; otherwise, the fuzzy standard is not met.

[0032] Furthermore, the original evaluation threshold T, the average hardness value H of the fruit that did not meet the fuzzy standard avg , standard value H standard ;

[0033] The dynamic adjustment calculation model is constructed based on the following formula:

[0034]

[0035] Wherein, T1 represents the revised assessment threshold, α and γ are adjustment coefficients, and Q represents the amount of fruit whose firmness value exceeds the standard value; the value ranges of α and γ are both between 0 and 1.

[0036] A method for assessing the maturity of macadamia nuts comprises the following steps:

[0037] S1. Evenly configure monitoring points according to the area of ​​the target park, obtain the real-time density of macadamia nuts at each monitoring point in real time, and during the estimated maturity period, when the real-time density curve at any monitoring point shows a downward trend over time, monitor the current monitoring point, obtain the time point when the real-time density drops from the maximum value to the predetermined interval calibration value, and trigger the maturity assessment mechanism at this time point;

[0038] S2. Execute the maturity assessment mechanism, randomly obtain the image data of M fallen macadamia nuts at the corresponding monitoring point, use edge detection and texture analysis technology to obtain the comparison data set of each macadamia nut, build a rule engine, compare the data in the comparison data set with the corresponding defined threshold, and calibrate and calculate the maturity level value at the corresponding monitoring point based on the comparison result;

[0039] S3. Based on the maturity grade value and the spectral analysis results, a weighted calculation model is constructed to generate a maturity estimate for the target park, and the preset assessment threshold of the maturity estimate is compared to determine whether the maturity of the macadamia nuts in the target park meets the fuzzy standard.

[0040] If the fuzzy meets the standard, the result will be output;

[0041] If the fuzziness does not meet the target, the analysis adjustment strategy is triggered;

[0042] S4. Execute the analysis and adjustment strategy, extract the macadamia nut fruits whose maturity does not meet the fuzzy standard and the number of fruits S in the target park, perform hardness analysis and measurement on the fruits that do not meet the fuzzy standard, obtain the hardness value of each fruit, and compare each hardness value with the standard value to obtain the proportion of fruits with hardness values ​​exceeding the standard value. Combined with the collected adjustment data set, a dynamic adjustment calculation model is constructed to generate a revised evaluation threshold. The revised evaluation threshold is compared with the maturity estimate for a second time, and whether the maturity of the macadamia nut in the target park meets the standard is determined based on the comparison results.

[0043] (III) Beneficial effects

[0044] The present invention provides a macadamia nut maturity assessment system, which has the following beneficial effects:

[0045] (1) This scheme ensures comprehensive and efficient monitoring coverage by setting a reasonable ratio of monitoring points to floor area. At the same time, the real-time density change curve is used to timely capture subtle changes in the early stage of fruit maturity. When the density drops to a preset threshold, the maturity assessment mechanism is automatically triggered, which improves the accuracy and timeliness of the assessment. This method not only optimizes the use of monitoring resources, but also reduces the inappropriate picking time caused by misjudgment of fruit maturity, thereby ensuring the yield and quality of macadamia nuts and improving the level of intelligence and economic benefits of agricultural production.

[0046] (2) This solution achieves accurate assessment and intelligent management of the maturity of macadamia nuts, accurately identifies the cracks and texture characteristics of nuts, and determines the maturity level in combination with the rule engine, effectively solving the problem of strong subjectivity and low accuracy of traditional assessment methods. At the same time, near-infrared spectroscopy technology is used to detect fatty acid content, and a weighted calculation model is constructed in combination with the maturity level value to scientifically assess the overall maturity of the park. By comparing with the preset threshold, a preliminary fuzzy judgment of maturity is achieved. This solution integrates image recognition and spectral analysis technology, which not only improves the accuracy and objectivity of the assessment, but also enhances the adaptability and robustness of the model.

[0047] (3) This scheme realizes the refined assessment and dynamic adjustment of the maturity of macadamia nuts, analyzes the hardness of fruits that do not meet the fuzzy standard, combines the hardness value, standard value and adjustment data set, builds a dynamic adjustment calculation model, and generates a revised assessment threshold, which effectively solves the problem of inaccurate assessment results caused by fixed thresholds in traditional assessment methods;

[0048] By introducing two adjustment items, namely the abnormal hardness ratio and the average hardness deviation, the hardness of substandard fruits is comprehensively considered, and the evaluation threshold can be finely adjusted, thereby improving the accuracy and flexibility of the evaluation. At the same time, the technical solution only triggers the adjustment mechanism when it is initially determined that the fruit is not fuzzy standard-compliant, thus ensuring the stability and efficiency of the evaluation process. By dynamically adjusting the evaluation threshold, the actual maturity of the fruit can be more accurately reflected, providing a scientific basis for agricultural production, helping to optimize picking decisions, and to a certain extent improving yield and quality, further promoting the development of smart agriculture. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a modular schematic diagram of a macadamia maturity assessment system in the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] Embodiment 1:

[0052] See also Figure 1 , this embodiment provides a macadamia nut maturity assessment system;

[0053] Traditionally, the maturity assessment of macadamia nuts (also known as Hawaiian nuts) mainly relies on manual visual inspection, touch to feel the hardness of the shell, and empirical judgment; these methods have the problems of strong subjectivity, low efficiency, and difficulty in standardization. Especially in large-scale plantations, it is difficult to achieve rapid and accurate assessment; considering special scenarios, such as night assessment, rapid screening of large-scale plantations, and the need to reduce manual contact to reduce the spread of pests and diseases, this system design will combine modern sensing technology and image recognition technology to realize an intelligent and automated maturity assessment system;

[0054] The evaluation system includes various functional modules, namely, monitoring trigger module, image processing module, spectrum analysis module and detection adjustment module; the system functional modules are described as follows:

[0055] The monitoring trigger module evenly configures monitoring points according to the area of ​​the target park, and the ratio between monitoring points and area is 1:30; the real-time density of macadamia nuts at each monitoring point is obtained in real time; during the maturity estimation period, when the real-time density change curve at any monitoring point shows a downward trend over time, the current monitoring point is monitored: the time point when the real-time density drops from the maximum value to the predetermined interval calibration value, and the maturity assessment mechanism is triggered at this time point;

[0056] Among them, the number of required monitoring points is set as follows:

[0057] If the area is less than 30 square meters, a monitoring point is configured at the center of the target park; if the area is not an integer multiple of 30, the number of monitoring points is: the current area is a multiple of 30, rounded up, for example: if the area is 70, then the area is 2.3 times 30, and the number of monitoring points after rounding up is 3;

[0058] The uniform configuration of monitoring points is explained by example:

[0059] If the number of monitoring points configured in the target park is 4, the target park is divided into four equal parts, and a high-definition camera is configured at the center of each area. The high-definition camera is used to monitor one or several fruit trees.

[0060] Estimated maturity period:

[0061] Indicates the period of maturity of macadamia nuts in the region and climate of the general target park. This period is obtained from the historical data of the earliest and latest time points of macadamia nut maturity, so as to obtain the maturity estimation period {earliest time point, latest time point}; for example {July 10, August 10}, this example is for reference and understanding only;

[0062] Real-time density of macadamia nuts:

[0063] It indicates the fruit density (i.e. the real-time density of macadamia nuts) within the fixed image interval captured by the high-definition camera at the corresponding monitoring point. The real-time density increases as the fruit tree grows. When it increases to a certain value, it means that the fruit has taken shape and the number will no longer increase. Then, some fruits will fall from the tree after they mature. At this time, the fruit density within the fixed image interval decreases over time, indicating that the fruit tree is ripe and falling off. However, not all fallen fruits fall due to ripeness, so it is necessary to set a value to determine whether the familiarity assessment mechanism needs to be triggered;

[0064] Graph:

[0065] The X-axis in the graph represents time, and the Y-axis represents real-time density, so the real-time density will change with time. When it reaches the highest point, it means that the real-time density has reached its maximum value. At this time, some ripe fruits fall, which will affect the real-time density. As more fruits fall, the real-time density curve shows a downward trend over time; among them, the preset interval calibration value represents: real-time density maximum value - 0.3% of the real-time density maximum value, then 0.3% of the real-time density maximum value represents the preset interval value, and the preset interval calibration value corresponding to the time point also indicates that the number of macadamia nuts falling at the monitoring point has reached a certain level.

[0066] By adopting the above technical solutions, we can scientifically configure monitoring points according to the target park area, and accurately identify the key nodes in the fruit ripening process by real-time monitoring of the density changes of macadamia nuts;

[0067] This technology effectively solves the problems of large assessment errors and waste of resources caused by uneven distribution of monitoring points and inaccurate monitoring timing in traditional agricultural monitoring. By setting a reasonable ratio of monitoring points to floor area, it ensures comprehensive and efficient monitoring coverage. At the same time, it uses real-time density change curves to timely capture subtle changes in the early stages of fruit maturity. When the density drops to a preset threshold, it automatically triggers the maturity assessment mechanism, improving the accuracy and timeliness of the assessment.

[0068] This method not only optimizes the use of monitoring resources, but also reduces the inappropriate timing of picking due to misjudgment of fruit maturity, thereby ensuring the yield and quality of macadamia nuts and improving the level of intelligence and economic benefits of agricultural production; in addition, this technical solution has strong adaptability and scalability, and can be promoted and applied to maturity monitoring of other fruit trees, providing strong support for the development of smart agriculture.

[0069] The image processing module executes the maturity assessment mechanism, randomly obtains the image data of M fallen macadamia nuts at the corresponding monitoring point, uses edge detection and texture analysis technology to obtain the comparison data set of each macadamia nut, builds a rule engine, compares the data in the comparison data set with the corresponding defined threshold, and calibrates and calculates the maturity level value at the corresponding monitoring point based on the comparison result; the value of M is at least 3, and usually 10;

[0070] Among them, the comparison data set includes the number of cracks and texture contrast;

[0071] The Canny edge detection algorithm identifies the number of cracks, and the texture contrast is calculated by GLCM; Gray-level co-occurrence matrix (GLCM): used to describe the spatial dependence of gray levels in an image;

[0072] The comparison results are as follows:

[0073] For each fallen macadamia nut, if the number of cracks exceeds the corresponding definition threshold and the texture contrast is lower than the corresponding definition threshold, the maturity grade of the corresponding macadamia nut is calibrated as Level 2; if the number of cracks is lower than the corresponding definition threshold and the texture contrast exceeds the corresponding definition threshold, the maturity grade of the corresponding macadamia nut is calibrated as Level 1;

[0074] Level 2 indicates that the macadamia nuts are at a higher level of maturity;

[0075] Grade 1 indicates that the macadamia nuts are less mature;

[0076] It should be noted that if the detected dropped macadamia nut is neither Grade 1 nor Grade 2, the macadamia nut will be discarded. However, generally speaking, the above situation will not occur. If it does, the value of M calculated subsequently is the value of the corresponding number of macadamia nuts discarded. For the convenience of representation and calculation, it will continue to be represented by M.

[0077] The process of calculating the maturity level value at the corresponding monitoring point is as follows:

[0078] The maturity level of each of the M macadamia nuts is counted, and then the average is calculated. The resulting value is the maturity level value at the corresponding monitoring point. For example, if M=3, the first one is level 2, the second one is level 2, and the third one is level 1, then the maturity level value at the corresponding monitoring point is 2.5.

[0079] Spectral analysis module:

[0080] Based on the maturity grade value and the spectral analysis results, a weighted calculation model is constructed to generate a maturity estimate for the target park. The preset assessment threshold of the maturity estimate is then compared to determine whether the maturity of the macadamia nuts in the target park meets the fuzzy standard. If the fuzzy standard is met, the result is output; if the fuzzy standard is not met, the analysis adjustment strategy is triggered.

[0081] The process of spectral analysis is as follows:

[0082] The fatty acid content of M fallen macadamia nuts was analyzed by near infrared spectrometer, so the fatty acid content of each macadamia nut was the result of spectral analysis;

[0083] The process of constructing a weighted calculation model is as follows:

[0084] The fatty acid content of M macadamia nuts was depolarized and then averaged to obtain the mean fatty acid content. The mean fatty acid content and maturity grade value were dimensionless and then weighted calculated. The formula is:

[0085] Gy=F1*Zs avg +F2*Cd;

[0086] In the formula, Gy represents the maturity estimation, F1 and F2 are weight coefficients, and F1+F2=1, Zs avg represents the mean value of fatty acid content, and Cd represents the maturity grade value;

[0087] The weight coefficient is determined by the coefficient of variation method, which is a method of assigning weights to each indicator according to the degree of variation between the current value of each evaluation indicator and the target value. If the numerical difference of a certain indicator is large, it can clearly distinguish the evaluated objects, indicating that the indicator has rich information for distinguishing, and thus the indicator should be given a larger weight. On the contrary, if the numerical difference of each evaluated object on a certain indicator is small, then the ability of this indicator to distinguish the evaluated objects is weak, and thus the indicator should be given a smaller weight. This method directly uses the information contained in each indicator to obtain the weight of the indicator through calculation, so it is objective.

[0088] The preset assessment thresholds for maturity valuation are compared. The comparison process is as follows:

[0089] When the maturity valuation exceeds the assessment threshold, the fuzzy standard is determined to be met; otherwise, the fuzzy standard is not met.

[0090] By adopting the above technical solutions, accurate assessment and intelligent management of macadamia nut maturity are achieved. The cracks and texture characteristics of nuts are accurately identified through the image processing module, and the maturity level is determined by combining with the rule engine, which effectively solves the problem of strong subjectivity and low accuracy of traditional assessment methods.

[0091] At the same time, the spectral analysis module uses near-infrared spectroscopy technology to detect fatty acid content, and combines the maturity grade value to build a weighted calculation model to scientifically evaluate the overall maturity of the park. By comparing with the preset threshold, it realizes the fuzzy judgment of maturity. The solution integrates image recognition and spectral analysis technology, which not only improves the accuracy and objectivity of the evaluation, but also dynamically determines the weight through the coefficient of variation method, enhancing the adaptability and robustness of the model.

[0092] In addition, this technical solution can ensure the reliability of the evaluation results, provide a scientific basis for agricultural production, help optimize the timing of picking, improve yield and quality, promote the development of smart agriculture, and solve the problems of resource waste and low efficiency caused by inaccurate maturity assessment in agricultural production.

[0093] The detection and adjustment module executes the analysis and adjustment strategy, extracts the fruits of macadamia nuts in the target park whose maturity is not fuzzy up to the standard and the number of fruits S, performs hardness analysis and measurement on the fruits that are not fuzzy up to the standard, obtains the hardness value of each fruit, and compares each hardness value with the standard value to obtain the proportion of the number of fruits with hardness values ​​exceeding the standard value, that is, Q / S, where Q represents the number of fruits with hardness values ​​exceeding the standard value. Combined with the collected adjustment data set, a dynamic adjustment calculation model is constructed to generate a revised evaluation threshold, which is then compared with the maturity estimate for a second time, and whether the maturity of macadamia nuts in the target park meets the standard is determined based on the comparison results.

[0094] The adjusted data set includes:

[0095] The original evaluation threshold T, the average firmness value H of the fruit that did not meet the fuzzy standard avg , standard value H standard ;

[0096] The dynamic adjustment calculation model is constructed based on the following formula:

[0097]

[0098] Wherein, T1 represents the revised evaluation threshold, α and γ are adjustment coefficients, which are used to control the reduction degree of Q / S and hardness deviation to the original evaluation threshold T respectively; the value range of α and γ is between 0 and 1;

[0099] It should be noted that the impact of abnormal hardness ratio: α×Q / S represents the impact of the ratio of hardness values ​​exceeding the standard value in the unambiguous standard fruits on the evaluation threshold; when this ratio increases, it means that the hardness of more unqualified fruits has actually approached or exceeded the standard, so the evaluation threshold should be lowered; the impact of average hardness deviation: It indicates the influence of the relative deviation between the average hardness value of the fruit that does not meet the standard and the standard hardness value on the evaluation threshold; when the average hardness value is higher than the standard value, this deviation is positive, indicating that the hardness of the fruit that does not meet the standard is generally high, so the evaluation threshold should also be lowered;

[0100] Comprehensive adjustment: By introducing two adjustment items (abnormal hardness ratio and average hardness deviation), the formula can more comprehensively reflect the hardness of substandard fruits and make more precise adjustments to the evaluation threshold. The above formula model is still triggered when it is initially determined to be not fuzzy standard-compliant. Only when the estimated maturity of the fruit does not exceed the original evaluation threshold T, we will further consider the hardness of the fruit and adjust the evaluation threshold according to the above formula.

[0101] By adopting the above technical solution, the refined assessment and dynamic adjustment of the maturity of macadamia nuts are realized. Through the detection and adjustment module, the hardness of fruits that do not meet the fuzzy standard is analyzed. Combining the hardness value, standard value and adjustment data set, a dynamic adjustment calculation model is constructed to generate a revised assessment threshold, which effectively solves the problem of inaccurate assessment results caused by fixed thresholds in traditional assessment methods.

[0102] This scheme introduces two adjustment items, namely the hardness abnormality ratio and the average hardness deviation, and comprehensively considers the hardness of fruits that do not meet the standards, thereby achieving fine adjustment of the evaluation threshold and improving the accuracy and flexibility of the evaluation. At the same time, this technical scheme only triggers the adjustment mechanism when it is initially determined that the fruit does not meet the fuzzy standard, ensuring the stability and efficiency of the evaluation process. By dynamically adjusting the evaluation threshold, it can more accurately reflect the actual maturity of the fruit, provide a scientific basis for agricultural production, help optimize picking decisions, improve yield and quality, further promote the development of smart agriculture, and solve the problems of inaccurate maturity assessment and waste of resources caused by fixed evaluation thresholds in agricultural production.

[0103] Embodiment 2:

[0104] Based on Example 1, this example also provides a method for assessing the maturity of macadamia nuts, comprising the following steps:

[0105] S1. Evenly configure monitoring points according to the area of ​​the target park, obtain the real-time density of macadamia nuts at each monitoring point in real time, and during the estimated maturity period, when the real-time density curve at any monitoring point shows a downward trend over time, monitor the current monitoring point, obtain the time point when the real-time density drops from the maximum value to the predetermined interval calibration value, and trigger the maturity assessment mechanism at this time point;

[0106] S2. Execute the maturity assessment mechanism, randomly obtain the image data of M fallen macadamia nuts at the corresponding monitoring point, use edge detection and texture analysis technology to obtain the comparison data set of each macadamia nut, build a rule engine, compare the data in the comparison data set with the corresponding defined threshold, and calibrate and calculate the maturity level value at the corresponding monitoring point based on the comparison result;

[0107] S3. Based on the maturity grade value and the spectral analysis results, a weighted calculation model is constructed to generate a maturity estimate for the target park, and the preset assessment threshold of the maturity estimate is compared to determine whether the maturity of the macadamia nuts in the target park meets the fuzzy standard.

[0108] If the fuzzy meets the standard, the result will be output;

[0109] If the fuzziness does not meet the target, the analysis adjustment strategy is triggered;

[0110] S4. Execute the analysis and adjustment strategy, extract the macadamia nut fruits whose maturity does not meet the fuzzy standard and the number of fruits S in the target park, perform hardness analysis and measurement on the fruits that do not meet the fuzzy standard, obtain the hardness value of each fruit, and compare each hardness value with the standard value to obtain the proportion of fruits with hardness values ​​exceeding the standard value. Combined with the collected adjustment data set, a dynamic adjustment calculation model is constructed to generate a revised evaluation threshold. The revised evaluation threshold is compared with the maturity estimate for a second time, and whether the maturity of the macadamia nut in the target park meets the standard is determined based on the comparison results.

[0111] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0112] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0113] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be covered by the protection scope of the present application.

Claims

1. A macadamia nut maturity assessment system, characterized in that: The system includes: The monitoring trigger module evenly configures monitoring points according to the area of ​​the target park, obtains the real-time density of macadamia nuts at each monitoring point in real time, and monitors the current monitoring point to obtain the time point when the real-time density drops from the maximum value to the predetermined interval calibration value during the maturity estimation period. The maturity assessment mechanism is triggered at this time point; The image processing module executes the maturity assessment mechanism, randomly obtains the image data of M fallen macadamia nuts at the corresponding monitoring point, uses edge detection and texture analysis technology to obtain the comparison data set of each macadamia nut, builds a rule engine, compares the data in the comparison data set with the corresponding defined threshold, and calibrates and calculates the maturity level value at the corresponding monitoring point based on the comparison result; The spectral analysis module builds a weighted calculation model based on the maturity grade value and the spectral analysis results to generate a maturity estimate for the target park, and compares the preset assessment threshold of the maturity estimate to determine whether the maturity of the macadamia nuts in the target park meets the fuzzy standard; If the fuzzy meets the standard, the result will be output; If the fuzziness does not meet the target, the analysis adjustment strategy is triggered; The detection and adjustment module executes the analysis and adjustment strategy, extracts the macadamia nuts in the target park whose maturity does not meet the fuzzy standard and the number of fruits S, performs hardness analysis and measurement on the fruits that do not meet the fuzzy standard, obtains the hardness value of each fruit, and compares each hardness value with the standard value to obtain the proportion of fruits with hardness values ​​exceeding the standard value. Combined with the collected adjustment data set, a dynamic adjustment calculation model is constructed to generate a revised evaluation threshold, which is compared with the maturity estimate for a second time, and whether the maturity of the macadamia nuts in the target park meets the standard is determined based on the comparison results.

2. A macadamia nut maturity assessment system according to claim 1, characterized in that: The ratio between monitoring points and floor area is 1:

30. The number of monitoring points is set as follows: if the floor area is less than 30, monitoring points are configured at the center of the target park; if the floor area is not an integer multiple of 30, the number of monitoring points is: the current floor area is rounded up to the integer of 30.

3. The macadamia nut maturity assessment system according to claim 1, characterized in that: The preset interval calibration value represents: the real-time density maximum value - 0.3% of the real-time density maximum value, and 0.3% of the real-time density maximum value represents the preset interval value.

4. The macadamia nut maturity assessment system according to claim 1, characterized in that: The comparison data set includes the number of cracks and texture contrast; the number of cracks is identified by the Canny edge detection algorithm, and the texture contrast is calculated by GLCM.

5. The macadamia nut maturity assessment system according to claim 1, characterized in that: The data in the comparison data set are compared with the corresponding definition threshold, and the comparison results are as follows: for each fallen macadamia nut, if the number of cracks exceeds the corresponding definition threshold and the texture contrast is lower than the corresponding definition threshold, the maturity grade of the corresponding macadamia nut is calibrated as level two; if the number of cracks is lower than the corresponding definition threshold and the texture contrast exceeds the corresponding definition threshold, the maturity grade of the corresponding macadamia nut is calibrated as level one.

6. A macadamia nut maturity assessment system according to claim 5, characterized in that: The process of obtaining the maturity level value at the corresponding monitoring point is as follows: Count the maturity level of each of the M macadamia nuts; The average calculation is performed, and the value obtained is the maturity level value at the corresponding monitoring point; The value of M is at least 3 and is a positive integer.

7. A macadamia nut maturity assessment system according to claim 6, characterized in that: The process of spectral analysis is: the fatty acid content of M fallen macadamia nuts is analyzed by near-infrared spectrometer, so the fatty acid content of each macadamia nut is the result of spectral analysis.

8. The macadamia nut maturity assessment system according to claim 7, characterized in that: The process of constructing a weighted calculation model is as follows: The fatty acid content of M macadamia nuts was depolarized; Perform mean calculation to obtain the mean value of fatty acid content; The mean value of fatty acid content and maturity grade value were dimensionless and then weighted calculated. The formula is: <h2 style=";text-align:left;direction:ltr">Gy=F1*Zs<h2 style=";text-align:left;direction:ltr"> avg <h2 style=";text-align:left;direction:ltr"> +F2*Cd; In the formula, Gy represents the maturity estimation, F1 and F2 are weight coefficients, and F1+F2=1, Zs avg represents the mean fatty acid content, and Cd represents the maturity grade value.

9. The macadamia nut maturity assessment system according to claim 1, characterized in that: The preset assessment thresholds for maturity valuation are compared. The comparison process is as follows: When the maturity valuation exceeds the assessment threshold, the fuzzy standard is determined to be met; otherwise, the fuzzy standard is not met.

10. The macadamia nut maturity assessment system according to claim 1, characterized in that: The adjusted data set includes: the original evaluation threshold T, the average firmness value H of the unfuzzified qualified fruits avg , standard value H standard ; The dynamic adjustment calculation model is constructed based on the following formula: Wherein, T1 represents the revised assessment threshold, α and γ are adjustment coefficients, and Q represents the amount of fruit whose firmness value exceeds the standard value; the value ranges of α and γ are both between 0 and 1.

Images