A high spectrum imaging based middling wheat imperfect grain detection system

Abstract

This invention relates to the field of agricultural detection technology, and more particularly to a hyperspectral imaging-based system for detecting imperfect grains in medium-gluten wheat. The system comprises a monitoring execution module for performing hyperspectral imaging detection on target monitored production lines; an imaging analysis module for determining the imaging execution status of each target monitored point based on an anomaly coverage index and an execution anomaly percentage index; an execution optimization module for determining whether to perform anomaly integration analysis or risk integration analysis on each key monitored point based on the current imaging execution status; an integration analysis module for determining whether to send an imaging risk warning to the user based on the continuous evaluation index or offset correlation index of each deviation verification set; and an integration analysis module for determining whether to send an imaging risk warning to the user based on a reference continuous evaluation index and an integration stage matching index. This invention improves the monitoring quality and analysis efficiency of the hyperspectral detection process.

Description

Technical Field

[0001] This invention relates to the field of agricultural testing technology, and in particular to a system for detecting imperfect grains in medium-gluten wheat based on hyperspectral imaging. Background Technology

[0002] The detection results of imperfect wheat grains are of great significance in ensuring food security and the quality of the grain industry. Hyperspectral detection can effectively save human resources. However, in the actual process of detecting imperfect wheat grains, there are various imaging interference factors. It is necessary to continuously analyze the anomalies of the acquired spectral images to ensure effective supervision of the hyperspectral detection process. However, this can easily create an additional data analysis burden on the hyperspectral detection process, thereby affecting the actual analysis efficiency. Therefore, it is necessary to find a way to combine the acquired spectral images with targeted analysis of the hyperspectral detection process in order to reduce the consumption of data analysis resources while ensuring effective supervision of the hyperspectral imaging process.

[0003] Chinese patent application publication number CN120563928A discloses a method for detecting abnormal appearance of single wheat grains based on deep learning models and hyperspectral imaging, including: Step 1, collecting wheat grain samples of different categories; Step 2, acquiring hyperspectral image data of wheat grains using visible-near-infrared and short-wave near-infrared hyperspectral imaging systems, and extracting spectral and image information; Step 3, preprocessing the spectral data and verifying the preprocessing effect; Step 4, screening spectral feature bands, extracting texture and morphological features by combining gray-level co-occurrence matrix, and constructing a mid-level data fusion model; Step 5, constructing a deep learning model for spectral feature fusion to achieve high-level fusion of spectral and image features; Step 6, performing pixel-level classification on the hyperspectral images to generate a spatial distribution visualization result of wheat grain appearance abnormalities. However, the above scheme has the following drawbacks: it fails to combine the actually acquired spectral images for targeted analysis of the hyperspectral detection process, resulting in high data analysis resource consumption in the actual monitoring process of imperfect wheat grains. Summary of the Invention

[0004] To address this issue, the present invention provides a hyperspectral imaging-based system for detecting imperfect grains in medium-gluten wheat, which overcomes the problem that existing technologies fail to combine the acquired spectral images with targeted analysis of the hyperspectral detection process, resulting in high data analysis resource consumption in the actual monitoring process of imperfect wheat grains.

[0005] To achieve the above objectives, the present invention provides a system for detecting imperfect grains in medium-gluten wheat based on hyperspectral imaging, comprising:

[0006] The monitoring execution module includes several target monitoring points for hyperspectral imaging detection of the target monitored production line;

[0007] An imaging analysis module, which is connected to the monitoring execution module, is used to determine the imaging execution status of each key monitoring point based on the anomaly coverage index and the execution anomaly percentage index. The key monitoring points are determined based on the stage false detection index and the spectral reflectance anomaly index.

[0008] An optimization module is executed, which is connected to the imaging analysis module, to determine whether to perform anomaly integration analysis or risk integration analysis for each key monitoring point based on the current imaging execution state.

[0009] An integrated analysis module, connected to the execution optimization module, is used to determine whether to perform integrated verification processing on the analysis deviation area of ​​the key regulatory point based on the abnormal overlap assessment index. Specifically, it determines whether to send an imaging risk warning to the user based on the continuous assessment index or offset correlation index of each deviation verification set of the key regulatory point, and determines whether to send an environmental fluctuation interference warning to the user for independent and scattered points based on the deviation stage matching index.

[0010] The integration analysis module, which is connected to both the execution optimization module and the integration analysis module, is used to determine whether to send an imaging risk warning to the user based on the reference continuous assessment index of key regulatory points and the integration phase matching index.

[0011] Furthermore, the imaging analysis module periodically detects the imaging evaluation index of each target monitoring point to determine key monitoring points;

[0012] The key monitoring points are target monitoring points whose imaging evaluation index is greater than the preset imaging evaluation index.

[0013] The imaging evaluation index is positively correlated with the stage false detection index and the spectral reflectance anomaly index.

[0014] Furthermore, the imaging execution state includes a first preset imaging execution state and a second preset imaging execution state;

[0015] The imaging analysis module records key monitoring points that are in the first preset imaging execution state as either an abnormality coverage index greater than a preset abnormality coverage index or an execution abnormality percentage index greater than a preset execution abnormality percentage index.

[0016] The imaging analysis module records key monitoring points that are in the second preset imaging execution state as having an anomaly coverage index less than or equal to a preset anomaly coverage index and an execution anomaly percentage index less than or equal to a preset execution anomaly percentage index.

[0017] Furthermore, the integrated analysis module performs anomaly integrated analysis on key monitoring points in the first preset imaging execution state, wherein,

[0018] The abnormal overlap assessment index of the key regulatory points is determined based on the analytical deviation area of ​​the key regulatory points within the target execution cycle.

[0019] Furthermore, the integrated analysis module performs integrated verification processing on the areas of analytical deviation existing in key regulatory points where the abnormal overlap assessment index is less than or equal to the abnormal overlap assessment index threshold.

[0020] The region coordinates corresponding to any analysis deviation region all have a validation validity index greater than the validation validity index threshold for the deviation validation set to which they belong.

[0021] Furthermore, the integrated analysis module responds to imaging risk conditions and sends imaging risk alerts to the user;

[0022] The imaging risk condition is that there is a deviation verification set at the key monitoring point where the continuous assessment index is greater than the preset continuous assessment index, or there is a deviation verification set where the offset correlation index is greater than the preset offset correlation index.

[0023] Furthermore, the method for setting the verification effectiveness index is determined based on the distribution index of overlapping areas of key regulatory points;

[0024] The integrated analysis module determines the verification validity index of the anomaly analysis coordinates corresponding to the deviation areas of key regulatory points whose overlapping area distribution index is greater than the preset overlapping area distribution index, based on the collaborative distribution parameters.

[0025] The integrated analysis module determines the verification validity index of the analysis deviation area corresponding to the abnormal analysis coordinates of the key regulatory points whose analysis deviation area distribution index is less than or equal to the preset analysis deviation area distribution index, based on the collaborative overlap parameters.

[0026] The overlapping area distribution index is determined based on the anomaly analysis coordinates of key regulatory points.

[0027] Furthermore, the integrated analysis module performs stage matching analysis on key regulatory points that have completed integrated verification processing, and detects the independent deviation dispersion index of key regulatory points.

[0028] The independent dispersion points are key regulatory points whose independent deviation dispersion index is greater than the preset independent deviation dispersion index. The independent deviation dispersion index is determined based on the independent deviation coordinates of the key regulatory points.

[0029] The independent deviation coordinates are the deviation area coordinates of key regulatory points within the target execution cycle, excluding the area coordinates within the deviation verification set. The deviation area coordinates are the area coordinates corresponding to the analytical deviation areas existing at key regulatory points within the target execution cycle.

[0030] Furthermore, the integrated analysis module responds to the stage matching conditions and sends environmental fluctuation interference alerts to the user;

[0031] The stage matching condition is that the deviation stage matching index is greater than the preset deviation stage matching index.

[0032] Furthermore, the integrated analysis module performs risk integration analysis on key regulatory points that are in a second preset imaging execution state or whose abnormal overlap assessment index is greater than the abnormal overlap assessment index threshold.

[0033] The integrated analysis module responds to integrated risk conditions and sends imaging risk alerts to the user;

[0034] The integrated risk condition is that the reference continuous assessment index of key regulatory points is greater than the preset reference continuous assessment index or the integration stage matching index is greater than the preset integration stage matching index.

[0035] Compared with existing technologies, the advantages of this invention are that the technical solution periodically evaluates the target regulatory points on the target regulatory production line to initially determine whether there are any abnormalities in the hyperspectral imaging process. Based on the abnormality coverage index and the execution abnormality ratio index, the imaging execution status of each target regulatory point is determined to determine whether to conduct abnormality integration analysis or risk integration analysis for each key regulatory point. This ensures that the imaging analysis scheme for key regulatory points is more in line with the actual situation and enables targeted analysis of the acquired spectral images. This invention improves analysis efficiency while ensuring the effectiveness of the assessment results of imaging risks at key regulatory points.

[0036] Furthermore, this invention determines the imaging execution status of each key regulatory point based on the anomaly coverage index and the execution anomaly percentage index. The anomaly coverage index and the execution anomaly percentage index characterize the richness of the imaging results corresponding to spectral reflectance anomalies obtained during the hyperspectral imaging detection process of each key regulatory point in the target execution cycle, as well as the wide range of spectral reflectance anomalies involved in the obtained imaging results. This characterizes the degree of analytical pressure and resource abundance during the imaging analysis process, thereby enabling targeted settings for the imaging analysis process. This achieves a balance between the quality and efficiency of regulatory analysis at different levels, and the invention improves the analytical efficiency of the assessment results of imaging risks.

[0037] Furthermore, this invention performs anomaly integration analysis on key monitoring points in the first preset imaging execution state. Based on the anomaly overlap assessment index, it determines whether to perform integration verification processing on the analysis deviation areas existing in the key monitoring points. The anomaly overlap assessment index characterizes the degree of overlap of the analysis deviation areas corresponding to the key monitoring points. For cases with a high degree of overlap, integration verification processing is performed. This reduces the resource consumption of the analysis process while identifying the existence of anomalies. Furthermore, the method of setting the verification effectiveness index is determined based on the overlap area distribution index of the key monitoring points to ensure the effectiveness of the setting results of the deviation verification set. This effectively integrates each analysis deviation area and further improves the efficiency of the assessment and analysis of imaging risks existing in key monitoring points.

[0038] Furthermore, this invention performs anomaly integration analysis on key regulatory points in the second preset imaging execution state or where the anomaly overlap assessment index is greater than the anomaly overlap assessment index threshold. Since the analysis pressure or overlap is relatively high during the imaging analysis of such key regulatory points, the overall anomaly is judged by integrating the regional coordinates corresponding to the analysis deviation areas within the target execution cycle. This avoids unnecessary consumption of analysis resources while ensuring an effective risk assessment of the hyperspectral imaging process for such key regulatory points. Attached Figure Description

[0039] Figure 1 This is a module connection diagram of the medium-gluten wheat imperfect grain detection system based on hyperspectral imaging of the present invention;

[0040] Figure 2 This is a flowchart illustrating the process of determining key monitoring points based on imaging evaluation indices in this invention.

[0041] Figure 3 This is a flowchart illustrating how the present invention determines the imaging execution status of each target monitoring point based on the anomaly coverage index and the execution anomaly percentage index.

[0042] Figure 4 This is a flowchart illustrating how the present invention determines whether to perform anomaly integration analysis or risk integration analysis on each key regulatory point based on the current imaging execution state. Detailed Implementation

[0043] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0044] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0045] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0046] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0047] Please see Figures 1 to 4 As shown, this invention provides a system for detecting imperfect grains in medium-gluten wheat based on hyperspectral imaging, comprising:

[0048] The monitoring execution module includes several target monitoring points for hyperspectral imaging detection of the target monitored production line;

[0049] An imaging analysis module, which is connected to the monitoring execution module, is used to determine the imaging execution status of each key monitoring point based on the anomaly coverage index and the execution anomaly percentage index. The key monitoring points are determined based on the stage false detection index and the spectral reflectance anomaly index.

[0050] An optimization module is executed, which is connected to the imaging analysis module, to determine whether to perform anomaly integration analysis or risk integration analysis for each key monitoring point based on the current imaging execution state.

[0051] An integrated analysis module, connected to the execution optimization module, is used to determine whether to perform integrated verification processing on the analysis deviation area of ​​the key regulatory point based on the abnormal overlap assessment index. Specifically, it determines whether to send an imaging risk warning to the user based on the continuous assessment index or offset correlation index of each deviation verification set of the key regulatory point, and determines whether to send an environmental fluctuation interference warning to the user for independent and scattered points based on the deviation stage matching index.

[0052] The integration analysis module, which is connected to both the execution optimization module and the integration analysis module, is used to determine whether to send an imaging risk warning to the user based on the reference continuous assessment index of key regulatory points and the integration phase matching index.

[0053] This invention is used to optimize the supervision of the quality testing process for wheat grains in a grain processing production line. The grain processing production line currently performing quality testing on wheat grains is designated as the target supervision production line. This target supervision production line has several hyperspectral detection points, each including: a line-scanning hyperspectral camera, an LED array light source, an industrial computer, a vibration sample delivery device, a simple airflow cleaning device, a pneumatic sorting device, a flow divider hopper, an integrated dustproof and shock-absorbing cover, and a standard whiteboard. Users can supplement and adjust these components according to the actual production scenario; this is easily understood by those skilled in the art and will not be elaborated upon here. However, it is necessary to ensure that each hyperspectral detection point can complete hyperspectral imaging and remove incomplete grains. Each hyperspectral detection point is designated as the target supervision point.

[0054] This invention utilizes several imaging monitoring records. Each imaging monitoring record records at least one imaging evaluation index, anomaly area proportion index, analysis anomaly coefficient, anomaly coverage index, execution anomaly proportion index, overlapping anomaly parameter, coordinate interval parameter, overlapping area distribution index, anomaly overlap evaluation index, continuous evaluation index, offset correlation index, verification validity index, independent deviation dispersion index, deviation stage matching index, reference continuous evaluation index, and integration stage matching index during the regulatory optimization process of quality monitoring of the target regulatory production line. Each imaging monitoring record also has a corresponding qualification mark. The qualification mark records whether the analysis quality of the hyperspectral detection process of wheat grains in the target regulatory production line meets the user's requirements. It can be understood that the user can determine whether the analysis quality of the hyperspectral detection process of wheat grains in the target regulatory production line meets the user's requirements based on self-defined indicators.

[0055] Specifically, the imaging analysis module periodically detects the imaging evaluation index of each target monitoring point to determine key monitoring points;

[0056] The key monitoring points are target monitoring points whose imaging evaluation index is greater than the preset imaging evaluation index.

[0057] The imaging evaluation index is positively correlated with the stage false detection index and the spectral reflectance anomaly index.

[0058] In this invention, an evaluation execution cycle is applied. The duration of the evaluation execution cycle can be determined by the user. The higher the user's requirements for the analytical quality of the hyperspectral detection process of wheat grains in the target monitored production line, the shorter the duration of the evaluation execution cycle. An evaluation execution cycle of 30 minutes is provided. At the end of each evaluation execution cycle, the imaging evaluation index of each target monitored point is detected.

[0059] If the current time is within an evaluation execution cycle, this evaluation execution cycle is recorded as the target execution cycle. The imaging evaluation index of each target monitoring point is detected. For a single target monitoring point, the imaging evaluation index is the sum of the stage false detection index and the spectral reflectance anomaly index. An initial assessment of the reliability of the imaging process at each target monitoring point is performed using the imaging evaluation index. The grain spectral image acquired by that target monitoring point within the target execution cycle is obtained. The spectral reflectance anomaly index... , This refers to the number of grain spectral images acquired at the target monitoring point within the target execution cycle. The stage false detection index is the number of abnormal spectral images acquired at the target monitoring point within the target execution cycle. , The removed grains obtained at the target monitoring point within the target execution cycle. The number of normal grains present in the removed grains obtained at the target monitoring point within the target execution cycle; the removed grains are the wheat grains removed after the target monitoring point is detected by hyperspectral imaging; the target monitoring point whose imaging evaluation index is less than or equal to the preset imaging evaluation index is recorded as the standard monitoring point.

[0060] The grain spectral image is a two-dimensional grayscale image corresponding to each band obtained during the hyperspectral image detection of wheat grains on the target monitoring production line at the target monitoring point. How to obtain the grain spectral image through hyperspectral imaging technology is a subject already mastered by those skilled in the art and will not be elaborated here. For a single target monitoring point, the imaging acquisition range corresponding to each grain spectral image obtained at the target monitoring point is consistent. The obtained grain spectral image is segmented to obtain several rectangular image regions of the same size, which are recorded as spectral analysis regions. For a single grain spectral image, if the abnormal region ratio index of the grain spectral image is greater than the preset abnormal region ratio index, the grain spectral image is recorded as an abnormal spectral image. The abnormal region ratio index is the proportion of the number of analytical deviation regions in the grain spectral image to the number of spectral analysis regions in the grain spectral image.

[0061] For a single spectral analysis region, if the analysis anomaly coefficient of that region is greater than a preset analysis anomaly coefficient, then that region is designated as an analysis deviation region. The analysis anomaly coefficient is the sum of the reflectance deviation index and the grayscale uniformity deviation index. , The reflectance of the band corresponding to this spectral analysis region. The grayscale uniformity deviation index is the average band reflectance of the reference analysis region corresponding to the spectral analysis region. , This represents the grayscale variation index corresponding to the spectral analysis region. This is the average grayscale variation index of the reference analysis region corresponding to the spectral analysis region. , This represents the average gray level of each pixel within the spectral analysis region. The standard deviation of the gray levels of each pixel within the spectral analysis region is given. Any reference analysis region within this spectral analysis region corresponds to the spectral band obtained during the acquisition process of this spectral analysis region and also has the same regional coordinates for the described grain spectral image. The regional coordinates for a single spectral analysis region are also specified. , This refers to the column order of the spectral analysis region when dividing the spectral image corresponding to that region. This refers to the row order of the spectral analysis region when dividing the spectral image corresponding to that region.

[0062] The values ​​of the preset imaging evaluation index, preset abnormal area proportion index, and preset analysis anomaly coefficient can be determined by the user based on the actual working scenario. For example, the user can set them based on imaging monitoring records. The higher the user's requirements for the analytical quality of the hyperspectral detection process of wheat grains in the target monitored production line, the smaller the value of the preset imaging evaluation index, the smaller the value of the preset abnormal area proportion index, and the smaller the value of the preset analysis anomaly coefficient. This provides a method for determining the value of the preset imaging evaluation index, which meets the user's analytical quality requirements for the hyperspectral detection process of wheat grains in the target monitored production line. The minimum value of the imaging evaluation index of key regulatory points is denoted as the preset imaging evaluation index. A method for determining the preset abnormal area proportion index is provided. The minimum value of the abnormal area proportion index of the abnormal spectral image in the imaging monitoring record that meets the user's analytical quality requirements for the hyperspectral detection process of wheat grains in the target regulatory production line is denoted as the preset abnormal area proportion index. A method for determining the preset analytical anomaly coefficient is provided. The minimum value of the analytical anomaly coefficient of the analytical deviation area in the imaging monitoring record that meets the user's analytical quality requirements for the hyperspectral detection process of wheat grains in the target regulatory production line is denoted as the preset analytical anomaly coefficient.

[0063] Specifically, the imaging execution state includes a first preset imaging execution state and a second preset imaging execution state;

[0064] The imaging analysis module records key monitoring points that are in the first preset imaging execution state as either an abnormality coverage index greater than a preset abnormality coverage index or an execution abnormality percentage index greater than a preset execution abnormality percentage index.

[0065] The imaging analysis module records key monitoring points that are in the second preset imaging execution state as having an anomaly coverage index less than or equal to a preset anomaly coverage index and an execution anomaly percentage index less than or equal to a preset execution anomaly percentage index.

[0066] Specifically, for a single key regulatory location, the anomaly coverage index... , The total number of spectral analysis regions obtained by dividing the spectral image of the grain corresponding to this key monitoring point. The number of overlapping anomalous regions in the spectral analysis area obtained by dividing the spectral image of the grain corresponding to the key monitoring point. For any analytical deviation region, if the overlapping anomalous parameter corresponding to the analytical deviation region is greater than a preset overlapping anomalous parameter, then the analytical deviation region is recorded as an overlapping anomalous region. The overlapping anomalous parameter... , This refers to the number of grain spectral images acquired at this key monitoring point within the target execution cycle. The number of related abnormal images corresponding to the analytical deviation region in the grain spectral images acquired at the key monitoring point within the target execution cycle; for a single grain spectral image acquired at the key monitoring point within the target execution cycle, if the reference analytical region corresponding to the analytical deviation region in the grain spectral image is the analytical deviation region, then the grain spectral image is recorded as a related abnormal image of the analytical deviation region; the execution abnormality ratio index. , The number of times hyperspectral imaging detection is performed at this key regulatory location within the target execution cycle. The number of detection execution anomalies at this key monitoring point within the target execution cycle is recorded as one detection execution anomaly. For each instance, a hyperspectral imaging detection is performed. If an abnormal spectral image is found in the acquired grain spectral image, it is recorded as one detection execution anomaly.

[0067] The values ​​of the preset anomaly coverage index, preset execution anomaly percentage index, and preset overlapping anomaly parameter can be determined by the user based on the actual working scenario. For example, the user can set them based on the imaging monitoring records. The higher the user's requirements for the analytical quality of the hyperspectral detection process of wheat grains in the target monitored production line, the smaller the value of the preset anomaly coverage index, the smaller the value of the preset execution anomaly percentage index, and the smaller the value of the preset overlapping anomaly parameter. This provides a method for determining the value of the preset anomaly coverage index, which will meet the user's requirements for the analytical quality of the hyperspectral detection process of wheat grains in the target monitored production line. The imaging monitoring records in the second preset imaging execution state... The maximum value of the anomaly coverage index of key monitoring points is denoted as the preset anomaly coverage index. A method for determining the preset execution anomaly ratio index is provided, which meets the user's analytical quality requirements for the hyperspectral detection process of wheat grains in the target monitored production line. The maximum value of the execution anomaly ratio index of key monitoring points in the second preset imaging execution state in the imaging monitoring record is denoted as the preset execution anomaly ratio index. A method for determining the preset overlapping anomaly difference parameter is provided, which meets the user's analytical quality requirements for the hyperspectral detection process of wheat grains in the target monitored production line. The minimum value of the overlapping anomaly parameter of the overlapping anomaly region in the imaging monitoring record is denoted as the preset overlapping anomaly parameter.

[0068] Specifically, the integrated analysis module performs anomaly integrated analysis on key monitoring points in the first preset imaging execution state, wherein...

[0069] The abnormal overlap assessment index of the key regulatory points is determined based on the analytical deviation area of ​​the key regulatory points within the target execution cycle.

[0070] Specifically, for a single key monitoring point, if the key monitoring point is in the first preset imaging execution state, the abnormal coverage index or execution abnormality ratio index of the key monitoring point is large, indicating that the key monitoring point has a large number of imaging results corresponding to spectral reflectance abnormalities during the hyperspectral imaging detection process in the target execution cycle, or that the range of spectral reflectance abnormalities in the acquired imaging results is wide. Therefore, it is necessary to perform anomaly integration analysis on the key monitoring point to ensure the analysis efficiency of the hyperspectral detection process.

[0071] For a single key regulatory point, the anomaly overlap assessment index is the average of the overlap anomaly assessment values ​​corresponding to the regional coordinates of all existing overlap anomaly regions within the target execution cycle. For the regional coordinates of a single existing overlap anomaly region, the overlap anomaly parameters of the overlap anomaly region corresponding to the regional coordinates should be consistent. The overlap anomaly parameters of the overlap anomaly region corresponding to the regional coordinates are recorded as the overlap anomaly assessment value. The anomaly overlap assessment index characterizes the degree of correlation of anomalies in the overall imaging results within the target execution cycle, thereby determining whether targeted integrated processing is needed for the key regulatory point.

[0072] Specifically, the integrated analysis module performs integrated verification processing on the areas of analytical deviation existing in key regulatory points where the abnormal overlap assessment index is less than or equal to the abnormal overlap assessment index threshold.

[0073] The region coordinates corresponding to any analysis deviation region all have a validation validity index greater than the validation validity index threshold for the deviation validation set to which they belong.

[0074] Specifically, for a single key regulatory point, if the abnormal overlap assessment index of the key regulatory point is less than or equal to the abnormal overlap assessment index threshold, it indicates that the analytical deviation area corresponding to the key regulatory point is relatively rich but the degree of overlap is low. Therefore, it is necessary to perform targeted integration processing on the analytical deviation area existing in the target execution cycle to improve the analytical efficiency of abnormal integration analysis of key regulatory points. The effective index is used to characterize the degree of overlap between the coordinates of the regions within each deviation verification set for the occurrence of imaging anomalies.

[0075] The deviation verification set is a set of several anomaly analysis coordinates. For a single key monitoring point, the coordinates of the overlapping anomaly areas existing at that key monitoring point within the target execution cycle are designated as anomaly analysis coordinates. The overlapping area distribution index is the average of the distribution evaluation parameters of each anomaly analysis coordinate. For a single anomaly analysis coordinate, the distribution evaluation parameters... , To assess the number of coordinates present in the distribution of this anomaly analysis coordinates, The distribution evaluation coordinates are the number of anomaly analysis coordinates included in the distribution evaluation coordinates where the anomaly analysis coordinates exist. The distribution evaluation coordinates are the region coordinates for which the coordinate interval parameter of the anomaly analysis coordinate is less than or equal to a preset coordinate interval parameter. For any two region coordinates, the coordinate interval parameter between the two region coordinates is... , This is the difference between the column order corresponding to the coordinates of the two regions mentioned above. This is the difference between the row order corresponding to the coordinates of the two regions mentioned above;

[0076] The values ​​of the preset coordinate interval parameter and the preset overlapping area distribution index can be determined by the user according to the actual working scenario. For example, the user can set them according to the imaging monitoring records. The higher the user's requirements for the analysis quality of the hyperspectral detection process of wheat grains in the target monitored production line, the larger the value of the preset coordinate interval parameter. A method for determining the value of the preset coordinate interval parameter is provided, in which the maximum value of the coordinate interval parameter of the distribution evaluation coordinate corresponding to the abnormal analysis coordinate in the integrated reference record that meets the user's analysis quality requirements for the hyperspectral detection process of wheat grains in the target monitored production line is recorded as the preset coordinate interval parameter. A method for determining the value of the overlapping area distribution index is provided, in which the imaging monitoring record that determines the verification effectiveness index based on the collaborative overlapping parameter is recorded as the distribution reference record, and the maximum value of the overlapping area distribution index in the distribution reference record that meets the user's analysis quality requirements for the hyperspectral detection process of wheat grains in the target monitored production line is recorded as the preset overlapping area distribution index.

[0077] The value of the abnormal overlap assessment index threshold can be determined by the user based on the actual working scenario. For example, the user can set it based on the imaging monitoring records. A method for determining the value of the abnormal overlap assessment index threshold is provided, in which the imaging monitoring records that are integrated for the analysis deviation area of ​​the key regulatory point are recorded as the integrated reference record, and the maximum value of the abnormal overlap assessment index in the integrated reference record that meets the user's analysis quality requirements for the hyperspectral detection process of wheat grains in the target regulatory production line is recorded as the abnormal overlap assessment index threshold.

[0078] Specifically, the integrated analysis module responds to imaging risk conditions and sends imaging risk alerts to the user;

[0079] The imaging risk condition is that there is a deviation verification set at the key monitoring point where the continuous assessment index is greater than the preset continuous assessment index, or there is a deviation verification set where the offset correlation index is greater than the preset offset correlation index.

[0080] Specifically, for any deviation verification set of a single key regulatory point, the continuous evaluation index... , This refers to the number of grain spectral images involved in the analytical deviation region corresponding to the anomaly analysis coordinates within the deviation verification set. The number of grain spectral images acquired at key monitoring points within the target execution cycle. If the continuous evaluation index of the deviation verification set is greater than the preset continuous evaluation index, it indicates that the duration of the region corresponding to the imaging anomaly is relatively long, which in turn indicates that there is a high probability of sensor anomaly in the hyperspectral detection process within the target execution cycle. Therefore, an imaging risk warning is sent to the user, and the offset correlation index of each deviation verification set whose continuous evaluation index is less than or equal to the preset continuous evaluation index is detected.

[0081] For any deviation verification set at a single key monitoring point, if the offset correlation index of the deviation verification set is greater than a preset offset correlation index, it indicates that the deviation verification set exhibits a regular offset, suggesting a high probability of optical component deviation during the hyperspectral detection process within the target execution cycle. Therefore, an imaging risk warning is sent to the user. The offset correlation index... , The number of offset evaluation sets is used to verify the existence of this bias. These are the coordinate deviation difference indices between the deviation verification set and its various offset assessment sets. The offset assessment sets of the deviation verification set are those containing the same number of anomaly analysis coordinates as the key regulatory target. For a single offset assessment set, the coordinate deviation difference index between the offset assessment set and the deviation verification set is... , The parameter representing the difference in coordinate interval between the offset evaluation set and the deviation verification set in column order is... The parameter representing the difference in coordinate interval between the offset evaluation set and the deviation verification set in terms of row order is... , To evaluate the standard deviation between the coordinate interval parameters of two regions within each column order, The average value of the coordinate interval parameter between the coordinates of two regions within each column order evaluation combination is used to define two regions whose coordinates are ordered in the same column order as the offset evaluation set and the deviation verification set, thus forming a column order evaluation combination. , To evaluate the standard deviation between the coordinate interval parameters of two regions within each row order combination, The average value of the coordinate interval parameter between two regions within each row order evaluation combination is used. Two regions whose coordinates are ordered in the same row order as the offset evaluation set and the deviation verification set are designated as a row order evaluation combination. If the deviation verification set does not contain an offset evaluation set, the deviation correlation index is recorded as 0. If so, the deviation correlation index is recorded as 1;

[0082] The values ​​of the preset continuous evaluation index and the preset offset correlation index can be determined by the user according to the actual working scenario. For example, the user can set them based on imaging monitoring records. The higher the user's requirements for the analytical quality of the hyperspectral detection process of wheat grains in the target supervised production line, the smaller the value of the preset continuous evaluation index and the preset offset correlation index. A method for determining the value of the preset continuous evaluation index is provided, in which the imaging monitoring record that sends imaging risk warnings to the user is recorded as the warning reference record, and the average value of the continuous evaluation index of the deviation verification parameter in the warning reference record that meets the user's analytical quality requirements for the hyperspectral detection process of wheat grains in the target supervised production line is recorded as the preset continuous evaluation index. A method for determining the value of the preset offset correlation index is provided, in which the minimum value of the offset correlation index of the deviation verification parameter in the warning reference record that meets the user's analytical quality requirements for the hyperspectral detection process of wheat grains in the target supervised production line is recorded as the preset offset correlation index.

[0083] Specifically, the method for setting the verification effectiveness index is determined based on the distribution index of overlapping areas of key regulatory points;

[0084] The integrated analysis module determines the verification validity index of the anomaly analysis coordinates corresponding to the deviation areas of key regulatory points whose overlapping area distribution index is greater than the preset overlapping area distribution index, based on the collaborative distribution parameters.

[0085] The integrated analysis module determines the verification validity index of the analysis deviation area corresponding to the abnormal analysis coordinates of the key regulatory points whose analysis deviation area distribution index is less than or equal to the preset analysis deviation area distribution index, based on the collaborative overlap parameters.

[0086] The overlapping area distribution index is determined based on the anomaly analysis coordinates of key regulatory points.

[0087] For key monitoring points where the distribution index of a single overlapping area is greater than the preset distribution index, since the distribution of anomaly analysis coordinates corresponding to these key monitoring points within the target execution cycle is relatively dense, it is necessary to conduct a collaborative analysis on the occurrence and distribution of each anomaly analysis coordinate to determine the verification validity index. This ensures that the determined deviation verification set setting can guarantee the spatial and temporal correlation between the regions containing imaging anomalies. For any anomaly analysis coordinate present at this key monitoring point, the collaborative distribution parameter... , This is the average value of the co-coincidence parameter of the anomaly analysis coordinate with respect to all anomaly analysis coordinates within its deviation verification set. This represents the number of anomaly analysis coordinates present in the deviation verification set to which the anomaly analysis coordinate belongs. The distribution evaluation coordinates of the anomaly analysis coordinates within the deviation verification set to which the anomaly analysis coordinates belong are evaluated. The co-distribution parameters of each anomaly analysis coordinate are normalized, and the normalized co-distribution parameters are recorded as the verification validity index of the corresponding anomaly analysis coordinates.

[0088] For key monitoring points where the distribution index of a single overlapping region is greater than the preset distribution index, since the distribution of the anomaly analysis coordinates corresponding to these key monitoring points within the target execution cycle is relatively scattered, the verification validity index can be determined solely by analyzing the synergistic occurrence of each anomaly analysis coordinate. This ensures that the determined deviation verification set setting guarantees the temporal correlation between the regions containing imaging anomalies. For any anomaly analysis coordinate at this key monitoring point, the average value of the synergistic overlap parameter of each anomaly analysis coordinate within its deviation verification set is normalized. The value obtained after normalization is recorded as the verification validity index of that anomaly analysis coordinate. For any two region coordinates, the synergistic overlap parameter... , This represents the number of different grain spectral images corresponding to the regions with analytical biases within the target execution cycle for the two regions mentioned above. The number of different grain spectral images corresponding to the analytical deviation regions existing in the above two regions within the target execution cycle;

[0089] The value of the verification validity index threshold can be determined by the user based on the actual working scenario. For example, the user can set it based on the imaging monitoring records. The higher the user's requirements for the analytical quality of the hyperspectral detection process of wheat grains in the target supervised production line, the larger the value of the verification validity index threshold. A method for determining the value of the verification validity index threshold is provided, which is the average value of the verification validity index of each analytical deviation region in the integrated reference record that meets the user's analytical quality requirements for the hyperspectral detection process of wheat grains in the target supervised production line to the deviation verification set to be recorded as the verification validity index threshold.

[0090] Specifically, the integrated analysis module performs stage matching analysis on key regulatory points that have completed integrated verification processing, and detects the independent deviation dispersion index of key regulatory points.

[0091] The independent dispersion points are key regulatory points whose independent deviation dispersion index is greater than the preset independent deviation dispersion index. The independent deviation dispersion index is determined based on the independent deviation coordinates of the key regulatory points.

[0092] The independent deviation coordinates are the deviation area coordinates of key regulatory points within the target execution cycle, excluding the area coordinates within the deviation verification set. The deviation area coordinates are the area coordinates corresponding to the analytical deviation areas existing at key regulatory points within the target execution cycle.

[0093] Specifically, the integrated analysis module responds to the matching conditions of the response stage and sends an environmental fluctuation interference prompt to the user;

[0094] The stage matching condition is that the deviation stage matching index is greater than the preset deviation stage matching index.

[0095] Specifically, for key regulatory points that have completed integrated verification processing, the independent deviation dispersion index is the average value of the deviation distribution evaluation parameters for each independent deviation coordinate existing at that key regulatory point. For a single independent deviation coordinate, the deviation distribution evaluation parameter... , To assess the number of coordinates present in the distribution of this independent deviation coordinate, The distribution of the anomaly analysis coordinates assesses the number of independent deviation coordinates included in the coordinate system, and the deviation stage matching index. , The number of times environmental assessment parameters were acquired during the period of deviation persistence. The number of environmental anomaly assessments corresponding to the deviation duration phase is defined as the number of times the environmental assessment parameters are temperature and humidity. For the end time of a single environmental assessment cycle, if the temperature or humidity obtained at that time is not within the corresponding preset range, it is recorded as an environmental anomaly assessment. The abnormal spectral images involved in the independent deviation coordinates are recorded as independent correlation images. The start time of the deviation duration phase is the acquisition time corresponding to the first independent correlation image obtained within the target execution cycle, and the end time of the deviation duration phase is the acquisition time corresponding to the last independent correlation image obtained within the target execution cycle.

[0096] In this invention, an environmental assessment cycle is applied. The duration of the environmental assessment cycle can be determined by the user. The higher the user's requirements for the analytical quality of the hyperspectral detection process of wheat grains in the target monitoring production line, the shorter the duration of the environmental assessment cycle. One environmental assessment cycle duration is provided as 5 minutes. At the end of each environmental assessment cycle, the temperature and humidity at the location of each target monitoring point are detected. How to obtain the temperature and humidity is a topic already known to those skilled in the art and is not limited to the specific device used, so it will not be described in detail here.

[0097] The values ​​of the preset independent deviation dispersion index and the preset deviation stage matching index can be determined by the user according to the actual working scenario. For example, the user can set them based on the imaging monitoring records. The higher the user's requirements for the analytical quality of the hyperspectral detection process of wheat grains in the target monitored production line, the larger the value of the preset independent deviation dispersion index and the preset deviation stage matching index. A method for determining the preset independent deviation dispersion index is provided, in which the minimum value of the independent deviation dispersion index of the independently dispersed points in the imaging monitoring records that meet the user's analytical quality requirements for the hyperspectral detection process of wheat grains in the target monitored production line is recorded as the preset independent deviation dispersion index. A method for determining the preset deviation stage matching index is provided, in which the imaging monitoring records that send environmental fluctuation interference prompts to the user are recorded as fluctuation reference records, and the average value of the deviation stage matching index in the fluctuation reference records that meet the user's analytical quality requirements for the hyperspectral detection process of wheat grains in the target monitored production line is recorded as the preset deviation stage matching index.

[0098] Specifically, the integrated analysis module performs risk integration analysis on key regulatory points that are in a second preset imaging execution state or whose abnormal overlap assessment index is greater than the abnormal overlap assessment index threshold.

[0099] The integrated analysis module responds to integrated risk conditions and sends imaging risk alerts to the user;

[0100] The integrated risk condition is that the reference continuous assessment index of key regulatory points is greater than the preset reference continuous assessment index or the integration stage matching index is greater than the preset integration stage matching index.

[0101] Specifically, for a single key monitoring point, if the key monitoring point is in the second preset imaging execution state, the abnormal coverage index and execution abnormality ratio index of the key monitoring point are both small, indicating that the imaging results corresponding to the spectral interference anomalies obtained during the hyperspectral imaging detection process of the key monitoring point within the target execution cycle are few and the coverage of spectral reflectance anomalies between the obtained imaging results is small. If the abnormal overlap assessment index of the key monitoring point is greater than the abnormal overlap assessment index threshold, it indicates that there are many analytical deviation areas corresponding to the execution abnormalities of each detection of the key monitoring point and the degree of overlap is high. Through risk integration analysis, an effective risk assessment can be made for the hyperspectral imaging process of such key monitoring points.

[0102] For a single key regulatory point, the reference continuous assessment index , This refers to the number of grain spectral images involved in the analysis of the deviation regions corresponding to the coordinates of the deviation regions at key monitoring points within the target execution cycle. The matching index in the integration phase refers to the number of grain spectral images acquired at key monitoring points within the target execution cycle. , For reference, the number of times environmental assessment parameters are obtained during the ongoing phase, To determine the number of environmental anomaly assessments within the reference duration phase, the start time of the reference duration phase is the acquisition time corresponding to the first abnormal spectral image acquired within the target execution cycle, and the end time of the reference duration phase is the acquisition time corresponding to the last abnormal spectral image acquired within the target execution cycle.

[0103] The values ​​of the preset reference continuous assessment index and the preset integration stage matching index can be determined by the user based on the actual working scenario. For example, the user can set them based on imaging monitoring records. The higher the user's requirements for the analytical quality of the hyperspectral detection process of wheat grains in the target regulated production line, the lower the value of the preset reference continuous assessment index and the lower the value of the preset integration stage matching index. A method for determining the value of the preset reference continuous assessment index is provided, in which the imaging monitoring record that sends imaging risk warnings to the user is recorded as the risk reference record, and the average value of the reference continuous assessment index in the risk reference record that meets the user's analytical quality requirements for the hyperspectral detection process of wheat grains in the target regulated production line is recorded as the preset reference continuous assessment index. A method for determining the value of the preset integration stage matching index is provided, in which the average value of the integration stage matching index in the risk reference record that meets the user's analytical quality requirements for the hyperspectral detection process of wheat grains in the target regulated production line is recorded as the preset integration stage matching index.

[0104] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A system for detecting imperfect grains in medium-gluten wheat based on hyperspectral imaging, characterized in that, include: The monitoring execution module includes several target monitoring points for hyperspectral imaging detection of the target monitored production line; An imaging analysis module, which is connected to the monitoring execution module, is used to determine the imaging execution status of each key monitoring point based on the anomaly coverage index and the execution anomaly percentage index. The key monitoring points are determined based on the stage false detection index and the spectral reflectance anomaly index. An optimization module is executed, which is connected to the imaging analysis module, to determine whether to perform anomaly integration analysis or risk integration analysis for each key monitoring point based on the current imaging execution state. An integrated analysis module, connected to the execution optimization module, is used to determine whether to perform integrated verification processing on the analysis deviation area of ​​the key regulatory point based on the abnormal overlap assessment index. Specifically, it determines whether to send an imaging risk warning to the user based on the continuous assessment index or offset correlation index of each deviation verification set of the key regulatory point, and determines whether to send an environmental fluctuation interference warning to the user for independent and scattered points based on the deviation stage matching index. An integrated analysis module, which is connected to the execution optimization module and the integrated analysis module respectively, is used to determine whether to send an imaging risk warning to the user based on the reference continuous assessment index of key regulatory points and the integration stage matching index. For a single key regulatory location, the anomaly coverage index , The total number of spectral analysis regions obtained by dividing the spectral image of the grain corresponding to this key monitoring point. The number of overlapping anomalous regions in the spectral analysis area obtained by dividing the spectral image of the corresponding key monitoring point; for any analysis deviation area, the overlapping anomalous parameter. , This refers to the number of grain spectral images acquired at this key monitoring point within the target execution cycle. The number of related abnormal images corresponding to the analytical deviation region in the grain spectral images acquired at this key monitoring point within the target execution cycle; the abnormal overlap assessment index is the average of the overlap anomaly assessment values ​​corresponding to the region coordinates of each existing overlap anomaly region at this key monitoring point within the target execution cycle; for the region coordinates of a single existing overlap anomaly region, the overlap anomaly parameter corresponding to that region coordinate is recorded as the overlap anomaly assessment value; the reference continuous assessment index... , This refers to the number of grain spectral images involved in the analysis of the deviation regions corresponding to the coordinates of the deviation regions at key monitoring points within the target execution cycle. The matching index in the integration phase refers to the number of grain spectral images acquired at key monitoring points within the target execution cycle. , For reference, the number of times environmental assessment parameters are obtained during the ongoing phase, The number of environmental anomaly assessments that occurred during the reference period; For a single target monitoring point, the spectral reflectance anomaly index , This refers to the number of grain spectral images acquired at the target monitoring point within the target execution cycle. The stage false detection index is the number of abnormal spectral images acquired at the target monitoring point within the target execution cycle. , The removed grains obtained at the target monitoring point within the target execution cycle. The number of normal grains present in the removed grains at the target monitoring point within the target execution cycle; For a single spectral analysis region, if the analysis anomaly coefficient of the spectral analysis region is greater than the preset analysis anomaly coefficient, then the spectral analysis region is recorded as an analysis deviation region. The deviation verification set is a set of several abnormal analysis coordinates, and the verification validity index of the region coordinates corresponding to any analysis deviation region with respect to the deviation verification set is greater than the verification validity index threshold. The continuous evaluation index is defined for any set of deviations at a single key regulatory point. , This refers to the number of grain spectral images involved in the analytical deviation region corresponding to the anomaly analysis coordinates within the deviation verification set. The offset correlation index is the number of grain spectral images acquired at key monitoring points within the target execution cycle. , The number of offset evaluation sets is used to verify the existence of this bias. These are the coordinate deviation difference indices between the deviation verification set and its respective offset evaluation sets; For a single independent deviation coordinate, the deviation stage matching index , The number of times environmental assessment parameters were acquired during the period of deviation persistence. This refers to the number of environmental anomaly assessments conducted during the deviation persistence phase.

2. The system for detecting imperfect grains in medium-gluten wheat based on hyperspectral imaging according to claim 1, characterized in that, The imaging analysis module periodically detects the imaging evaluation index of each target monitoring point to identify key monitoring points. The key monitoring points are target monitoring points whose imaging evaluation index is greater than the preset imaging evaluation index. The imaging evaluation index is positively correlated with the stage false detection index and the spectral reflectance anomaly index. The imaging evaluation index is the sum of the stage false detection index and the spectral reflectance anomaly index.

3. The system for detecting imperfect grains in medium-gluten wheat based on hyperspectral imaging according to claim 2, characterized in that, The imaging execution state includes a first preset imaging execution state and a second preset imaging execution state; The imaging analysis module records key monitoring points that are in the first preset imaging execution state as either an abnormality coverage index greater than a preset abnormality coverage index or an execution abnormality percentage index greater than a preset execution abnormality percentage index. The imaging analysis module records key monitoring points that are in the second preset imaging execution state as having an anomaly coverage index less than or equal to a preset anomaly coverage index and an execution anomaly percentage index less than or equal to a preset execution anomaly percentage index.

4. The system for detecting imperfect grains in medium-gluten wheat based on hyperspectral imaging according to claim 3, characterized in that, The integrated analysis module performs anomaly integrated analysis on key monitoring points in the first preset imaging execution state, wherein... The abnormal overlap assessment index of the key regulatory points is determined based on the analytical deviation area of ​​the key regulatory points within the target execution cycle.

5. The system for detecting imperfect grains in medium-gluten wheat based on hyperspectral imaging according to claim 4, characterized in that, The integrated analysis module performs integrated verification processing on the areas of analytical deviation existing in key regulatory points where the abnormal overlap assessment index is less than or equal to the abnormal overlap assessment index threshold. The region coordinates corresponding to any analysis deviation region all have a validation validity index greater than the validation validity index threshold for the deviation validation set to which they belong. The method for setting the verification effectiveness index is determined based on the overlapping area distribution index of key regulatory points, and the overlapping area distribution index is determined based on the anomaly analysis coordinates of key regulatory points.

6. The system for detecting imperfect grains in medium-gluten wheat based on hyperspectral imaging according to claim 5, characterized in that, The integrated analysis module responds to imaging risk conditions and sends imaging risk alerts to the user; The imaging risk condition is that there is a deviation verification set at the key monitoring point where the continuous assessment index is greater than the preset continuous assessment index, or there is a deviation verification set where the offset correlation index is greater than the preset offset correlation index.

7. The system for detecting imperfect grains in medium-gluten wheat based on hyperspectral imaging according to claim 6, characterized in that, The integrated analysis module determines the verification validity index of the anomaly analysis coordinates corresponding to the deviation areas of key regulatory points whose overlapping area distribution index is greater than the preset overlapping area distribution index, based on the collaborative distribution parameters. For any anomaly analysis coordinates present at key monitoring points, the collaborative distribution parameters... , This is the average value of the co-coincidence parameter of the anomaly analysis coordinate with respect to all anomaly analysis coordinates within its deviation verification set. This represents the number of anomaly analysis coordinates present in the deviation verification set to which the anomaly analysis coordinate belongs. The distribution of the anomaly analysis coordinates within the deviation verification set to which the anomaly analysis coordinates belong is evaluated to assess the number of coordinates. The integrated analysis module determines the verification validity index of the analysis deviation area corresponding to the abnormal analysis coordinates of the key regulatory points whose analysis deviation area distribution index is less than or equal to the preset analysis deviation area distribution index, based on the collaborative overlap parameters. For any two region coordinates, the cooperative coincidence parameter , This represents the number of different grain spectral images corresponding to the regions with analytical biases within the target execution cycle for the two regions mentioned above. The number of different grain spectral images corresponding to the analysis deviation regions existing in the above two regional coordinates within the target execution cycle.

8. The system for detecting imperfect grains in medium-gluten wheat based on hyperspectral imaging according to claim 7, characterized in that, The integrated analysis module performs stage matching analysis on key regulatory points that have completed integrated verification processing, and detects the independent deviation dispersion index of key regulatory points. The independent dispersion points are key regulatory points whose independent deviation dispersion index is greater than the preset independent deviation dispersion index. The independent deviation dispersion index is determined based on the independent deviation coordinates of the key regulatory points. The independent deviation coordinates are the deviation area coordinates of key regulatory points within the target execution cycle, excluding the area coordinates within the deviation verification set. The deviation area coordinates are the area coordinates corresponding to the analytical deviation areas existing in the key regulatory points within the target execution cycle. For key regulatory points that have completed integrated verification processing, the independent deviation dispersion index is the average of the deviation distribution evaluation parameters of each independent deviation coordinate existing at that key regulatory point. For a single independent deviation coordinate, the deviation distribution evaluation parameter... , To assess the number of coordinates present in the distribution of this independent deviation coordinate, The distribution of the anomaly analysis coordinates assesses the number of independent deviation coordinates included in the coordinate system.

9. The system for detecting imperfect grains in medium-gluten wheat based on hyperspectral imaging according to claim 8, characterized in that, The integrated analysis module responds to the matching conditions of the stage and sends environmental fluctuation interference prompts to the user. The stage matching condition is that the deviation stage matching index is greater than the preset deviation stage matching index.

10. The system for detecting imperfect grains in medium-gluten wheat based on hyperspectral imaging according to claim 9, characterized in that, The integrated analysis module performs risk integration analysis on key regulatory points that are in a second preset imaging execution state or whose abnormal overlap assessment index is greater than the abnormal overlap assessment index threshold. The integrated analysis module responds to integrated risk conditions and sends imaging risk alerts to the user; The integrated risk condition is that the reference continuous assessment index of key regulatory points is greater than the preset reference continuous assessment index or the integration stage matching index is greater than the preset integration stage matching index.

Images