Sweet potato root tuber growth state monitoring system based on spectral imaging analysis

Abstract

The invention relates to the technical field of data processing, in particular to a sweet potato root tuber growth state monitoring system based on spectral imaging analysis, and the system comprises a data collection module which is used for collecting a spectral signal curve of a target sweet potato root tuber and smoothing the spectral signal curve to obtain a target spectral signal curve; the curve division module is used for acquiring at least two continuous target spectral signal curves, mapping all the target spectral signal curves to the same two-dimensional plane, and dividing all the target spectral signal curves in the two-dimensional plane into at least two spectral signal sub-curve sets; the curve correction module is used for acquiring the soil reflection abnormal degree of the spectral signal sub-curve set and correcting the reflection intensity of each spectral signal on each target spectral signal curve; and the state monitoring module is used for monitoring the growth state of the target sweet potato tuberous roots according to each corrected target spectral signal curve, so that the accuracy of monitoring the growth state of the sweet potato tuberous roots is improved.

Description

Technical Field

[0001] The invention relates to the technical field of data processing, and in particular to a sweet potato root tuber growth state monitoring system based on spectral imaging analysis. Background Art

[0002] Water supply is one of the important factors affecting the growth and shape of sweet potatoes. The growth of sweet potatoes can be controlled by managing water supply, so as to obtain better potato shapes. Therefore, it is of great significance to monitor the growth status of sweet potatoes and adopt different water supply schemes during the growth of sweet potatoes. At present, spectral imaging technology is used to monitor the growth status of sweet potatoes: infrared light is emitted to the sweet potato tubers using infrared spectroscopy to obtain a spectral signal curve between 1400nm and 1900nm, and the spectral signal curve is compared with the standard spectral signal curve during normal growth of sweet potatoes to determine the obvious degree of the peak in the spectral signal curve. When there is a large difference between the spectral signal curve and the standard spectral signal curve, it indicates that the water absorption function of the sweet potato tubers is abnormal and the growth status is at risk of poor growth. This method can quickly and non-destructively monitor the growth and health status of sweet potatoes, thereby helping to optimize water management strategies and improve the quality of tuber shape.

[0003] However, when using spectral imaging technology to monitor the growth status of sweet potato roots, the humid particles in the soil will affect the reflected spectral signal, making the spectral signal easily interfered by the soil moisture and particle structure above the sweet potato roots, resulting in inaccurate spectral signals of the sweet potato roots actually collected, and thus the results of judging the growth status of the sweet potato based on the spectral signal are also biased.

[0004] Therefore, how to ensure the accuracy of the collection of spectral signals of sweet potato roots to reduce the error in monitoring the growth status of sweet potato roots has become an urgent problem to be solved. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a sweet potato root tuber growth status monitoring system based on spectral imaging analysis to solve the problem of how to ensure the accuracy of collecting spectral signals of sweet potato root tubers to reduce the error in monitoring the growth status of sweet potato root tubers.

[0006] An embodiment of the present invention provides a sweet potato root growth status monitoring system based on spectral imaging analysis, the system comprising:

[0007] A data acquisition module is used to collect infrared spectrum signals of target sweet potato tubers within a preset period, construct a corresponding spectrum signal curve, wherein the horizontal axis of the spectrum signal curve is wavelength, and the vertical axis is reflection intensity, and the spectrum signal curve is smoothed according to the peaks and valleys in the spectrum signal curve to obtain a target spectrum signal curve;

[0008] A curve division module, used to obtain target spectral signal curves within at least two consecutive preset periods, map all target spectral signal curves to the same two-dimensional plane, the horizontal axis of the two-dimensional plane is the wavelength, and the vertical axis is the reflection intensity, and divide all target spectral signal curves in the two-dimensional plane into at least two spectral signal sub-curve sets according to the inflection point of each target spectral signal curve in the two-dimensional plane;

[0009] A curve correction module, used for obtaining the soil reflection anomaly degree of the corresponding spectral signal sub-curve set according to the difference between each spectral signal sub-curve in each spectral signal sub-curve set, and correcting the reflection intensity of each spectral signal on each target spectral signal curve according to the soil reflection anomaly degree of each spectral signal sub-curve set to obtain a corrected target spectral signal curve;

[0010] The status monitoring module is used to monitor the growth status of the target sweet potato root tubers according to each of the corrected target spectral signal curves.

[0011] Preferably, the data acquisition module performs smoothing processing on the spectral signal curve according to the peaks and valleys in the spectral signal curve to obtain a target spectral signal curve, including:

[0012] Acquire the peak points and the trough points in the spectral signal curve, and for any point among the peak points and the trough points, acquire the degree of scattering anomaly of the any point according to the adjacent data points of the any point on the spectral signal curve;

[0013] If the scattering abnormality degree of any point is greater than or equal to a preset abnormality degree threshold, then the reflection intensity average between the left adjacent data point and the right adjacent data point of the any point is obtained, and the reflection intensity of the any point is replaced by the reflection intensity average; if the scattering abnormality degree of any point is less than the preset abnormality degree threshold, then the reflection intensity of the any point is kept unchanged;

[0014] Each of the wave peaks and each of the wave valleys is traversed to obtain a target spectrum signal curve.

[0015] Preferably, obtaining the degree of scattering anomaly of any point according to adjacent data points of any point on the spectral signal curve includes:

[0016] Calculate the absolute values ​​of the differences in reflection intensity between any point and its left adjacent data point and right adjacent data point respectively to obtain an average absolute value of the difference, and perform normalization processing on the average absolute value of the difference to obtain the local difference degree of any point;

[0017] Obtain a left adjacent wave crest point or a left adjacent wave trough point of any point on the spectral signal curve, count the number of left interval data points between any point and the left adjacent wave crest point or the left adjacent wave trough point, obtain the number of right interval data points between any point and its right adjacent wave crest point or the right adjacent wave trough point, and use a preset exponential function to inversely normalize the sum of the number of left interval data points and the number of right interval data points to obtain the degree of fluctuation continuation of any point;

[0018] The degree of scattering anomaly at any point is obtained according to the degree of local difference at any point and the degree of continuity of the fluctuation.

[0019] Preferably, the curve division module divides all target spectral signal curves in the two-dimensional plane into at least two spectral signal sub-curve sets according to the inflection point of each target spectral signal curve in the two-dimensional plane, including:

[0020] Cluster the inflection points of all target spectral signal curves in the two-dimensional plane to obtain at least two inflection point clustering clusters, obtain the center of gravity of each inflection point clustering cluster, draw a vertical line through each center of gravity according to the position of each center of gravity in the two-dimensional plane, and use the vertical line to divide all target spectral signal curves in the two-dimensional plane into at least two spectral signal sub-curve sets.

[0021] Preferably, the curve correction module obtains the soil reflectance anomaly degree of the corresponding spectral signal sub-curve set according to the difference between each spectral signal sub-curve in each spectral signal sub-curve set, including:

[0022] For any spectral signal sub-curve set, obtain the wavelength interval corresponding to the any spectral signal sub-curve set, take any wavelength in the wavelength interval as the target wavelength, and respectively calculate the absolute value of the difference in reflection intensity of every two adjacent spectral signal sub-curves in the any spectral signal sub-curve set corresponding to the target wavelength to obtain the cumulative sum of the absolute values ​​of the differences;

[0023] Obtaining the cumulative sum of absolute values ​​of the differences corresponding to each wavelength in the wavelength interval, and obtaining the mean of the cumulative sum of absolute values ​​of the differences as the degree of signal change difference of any spectral signal sub-curve set;

[0024] The signal change difference degree of each of the spectral signal sub-curve sets is obtained, and the soil reflectance anomaly degree of any of the spectral signal sub-curve sets is obtained according to the signal change difference degree of each of the spectral signal sub-curve sets.

[0025] Preferably, the step of obtaining the soil reflectance anomaly degree of any spectral signal sub-curve set according to the signal change difference degree of each spectral signal sub-curve set comprises:

[0026] The average value of the signal change difference degrees of all spectral signal sub-curve sets is calculated, the absolute value of the difference between the signal change difference degree of any spectral signal sub-curve set and the average value is calculated, recorded as the difference characteristic value, and the product of the difference characteristic value and the signal change difference degree of any spectral signal sub-curve set is normalized to obtain the soil reflectance anomaly degree of any spectral signal sub-curve set.

[0027] Preferably, the curve correction module corrects the reflection intensity of each spectral signal on each target spectral signal curve according to the soil reflection anomaly degree of each spectral signal sub-curve set to obtain a corrected target spectral signal curve, including:

[0028] The soil reflection anomaly degree of each of the spectral signal sub-curve sets is compared with a preset soil reflection anomaly degree threshold value. If the soil reflection anomaly degree of any spectral signal sub-curve set is less than the soil reflection anomaly degree threshold value, the reflection intensity of each spectral signal on each spectral signal sub-curve in the spectral signal sub-curve set is kept unchanged;

[0029] If the soil reflection anomaly degree of any spectral signal sub-curve set is greater than or equal to the soil reflection anomaly degree threshold, then the reflection intensity of each spectral signal on each spectral signal sub-curve in the arbitrary spectral signal sub-curve set is corrected to obtain a corrected spectral signal sub-curve set;

[0030] The spectral signal sub-curve in each of the modified spectral signal sub-curve sets is used to replace the corresponding spectral signal sub-curve in each of the target spectral signal curves to obtain each modified target spectral signal curve.

[0031] Preferably, the step of correcting the reflection intensity of each spectral signal on each spectral signal sub-curve in the arbitrary spectral signal sub-curve set to obtain a corrected spectral signal sub-curve set includes:

[0032] For any spectral signal on each spectral signal sub-curve in the arbitrary spectral signal sub-curve set, obtain the product of a preset multiple and the degree of soil reflection anomaly of the arbitrary spectral signal sub-curve set, and use the sum of a constant 1 and the product as a correction coefficient for the arbitrary spectral signal, and obtain the corrected reflection intensity of the arbitrary spectral signal according to the product of the correction coefficient and the reflection intensity of the arbitrary spectral signal.

[0033] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0034] The present invention analyzes the signal fluctuation characteristics of the spectral signal curve within each preset period of the target sweet potato root tuber, and adaptively smoothes each spectral signal curve according to the peak characteristics on the spectral signal curve to obtain the target spectral signal curve, so as to separate the possible soil scattering interference and smooth out the scattering interference abnormal points, and further combine the curve change difference characteristics of multiple target spectral signal curves to obtain the possibility that the spectral curve fluctuation may be interfered by soil reflection, that is, the degree of soil reflection abnormality, so as to correct the abnormal points that may be interfered by soil reflection, and obtain relatively accurate spectral curve data (corrected target spectral signal curve) that is not interfered by the soil above the sweet potato root tuber, thereby improving the accuracy of monitoring the growth status of the target sweet potato root tuber according to the corrected target spectral signal curve. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0036] Figure 1 It is a structural block diagram of a sweet potato root growth status monitoring system based on spectral imaging analysis provided in Example 1 of the present invention;

[0037] Figure 2 is a schematic diagram of a two-dimensional plane provided by an embodiment of the present invention;

[0038] Figure 3 It is a schematic diagram of dividing a target spectrum signal curve in a two-dimensional plane provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0039] Embodiments of the present disclosure are described in detail below, and examples of the embodiments are shown in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, but should not be understood as limiting the present disclosure.

[0040] It should be noted that the terms "first", "second", etc. in the specification of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure.

[0041] In order to illustrate the technical solution of the present invention, specific embodiments are provided below for illustration.

[0042] See also Figure 1 , is a structural block diagram of a sweet potato root growth status monitoring system based on spectral imaging analysis provided in Example 1 of the present invention, such as Figure 1 As shown, the system may include:

[0043] The data acquisition module 11 is used to collect infrared spectral signals of target sweet potato tubers within a preset period and construct a corresponding spectral signal curve, wherein the horizontal axis of the spectral signal curve is wavelength and the vertical axis is reflection intensity. According to the peaks and troughs in the spectral signal curve, the spectral signal curve is smoothed to obtain the target spectral signal curve.

[0044] The specific scenario targeted by the present invention is: when using an infrared light source and a spectral detector to monitor sweet potato roots, the spectral data of the sweet potato roots are collected because the soil above the roots will cause certain scattering and reflection of the infrared light, thereby masking the signal from the sweet potato roots, and ultimately causing the spectral signal actually received by the spectral detector to include the reflected signal of the soil, making the collection of the spectral signal of the sweet potato roots inaccurate, resulting in large errors in the monitoring of the growth status of the sweet potato roots based on the spectral signal.

[0045] Therefore, in order to solve the above problems, after irrigating the target sweet potato, infrared light is emitted to the target sweet potato root tuber using an infrared spectrum, and then a spectrum detector (such as FTIR or fiber optic spectrometer) is used to receive the reflected infrared spectrum signal, which is used to obtain the material characteristics of the target sweet potato root tuber by detecting the spectrum signal reflected by the target sweet potato root tuber. The reflection intensity of different wavelengths is separated from the received infrared spectrum signal to form a spectrum signal curve of the target sweet potato root tuber, wherein the horizontal axis of the spectrum signal curve is the wavelength and the vertical axis is the reflection intensity.

[0046] In the embodiment of the present invention, according to the above-mentioned spectral signal curve acquisition method, the spectral signal curve of the target sweet potato root tuber is continuously acquired multiple times, corresponding to a plurality of spectral signal curves within a monitoring period of 24 hours. Among them, the acquisition frequency of the spectral signal curve is once every 10 minutes, that is, the preset period is 10 minutes.

[0047] Due to the uneven size of soil particles, after the infrared spectral signal enters the soil, when the infrared light passes through the soil with uneven density distribution and complex soil particles, there is a possibility that infrared light scattering will occur. Therefore, in the embodiment of the present invention, firstly, the abnormal spectral signals that may be affected by scattering in each spectral signal curve are monitored, and the abnormal spectral signals are smoothed to eliminate the influence of the abnormal spectral signals caused by infrared light scattering. Then, after smoothing the abnormal spectral signals, the degree of influence of soil scattering on each spectral signal curve is analyzed to correct the actually collected spectral signals, so as to obtain spectral data that can more truly and accurately characterize the growth status of the target sweet potato root tubers.

[0048] Among them, for smoothing the abnormal spectral signal in each spectral signal curve, considering the influence of soil scattering, the spectral detector will receive unconventional spectral wavelengths, corresponding to which there will be a sudden change in the reflection intensity of some wavelengths, which is manifested in the spectral signal curve as a peak or valley point with a significant difference in reflection intensity from adjacent wavelengths, and is significantly different from the fluctuation of normal peak points or normal valley points. Secondly, since scattering will cause a sudden change in the reflection intensity of a certain wavelength in the normal spectral signal curve, the sudden change is manifested in a peak point or trough point composed of only a single coordinate point on the spectral signal curve, and the waveform where the peak point or trough point is located is relatively narrow, and the continuation of the fluctuation is weak. Therefore, in the embodiment of the present invention, taking a spectral signal curve as an example, the spectral signal curve is smoothed according to the peaks and troughs in the spectral signal curve to obtain the target spectral signal curve.

[0049] The peak points and trough points in the spectral signal curve are obtained by using the AMPD peak search algorithm. According to the difference between the adjacent data points of each peak point and each trough point, each peak point and trough point are traversed in turn to obtain the corresponding scattering anomaly degree. Specifically, for any point among the peak points and trough points, the absolute value of the difference in reflection intensity between the any point and its left adjacent data point and the right adjacent data point is calculated to obtain the average absolute value of the difference. The average absolute value of the difference is normalized to obtain the local difference degree of any point.

[0050] Obtain a left adjacent wave crest point or a left adjacent wave trough point of any point on the spectral signal curve, count the number of left interval data points between any point and the left adjacent wave crest point or the left adjacent wave trough point, obtain the number of right interval data points between any point and its right adjacent wave crest point or the right adjacent wave trough point, and use a preset exponential function to inversely normalize the sum of the number of left interval data points and the number of right interval data points to obtain the degree of fluctuation continuation of any point;

[0051] The degree of scattering anomaly at any point is obtained according to the degree of local difference at any point and the degree of continuity of the fluctuation.

[0052] In one embodiment, taking the i-th peak point as an example, the calculation expression of the scattering anomaly degree of the i-th peak point is:

[0053]

[0054] Among them, S i represents the degree of scattering anomaly of the i-th peak point, norm() represents the normalization function, || represents the absolute value symbol, x i represents the reflection intensity of the i-th wave crest point, x i,l represents the reflection intensity of the left adjacent data point of the i-th peak point, x i,r represents the reflection intensity of the right adjacent data point of the i-th wave peak point, exp() represents the exponential function with natural constant as the base, n i+1 Represents the number of data points between the i-th peak point and the i+1-th peak point, that is, the number of right interval data points, n i-1 Represents the number of data points between the i-th peak point and the i-1-th peak point, that is, the number of left interval data points.

[0055] It should be noted that It is used to characterize the degree of local difference of the i-th peak point. The greater the difference in reflection intensity between the i-th peak point and its left and right adjacent data points, the more obvious the abnormality of the i-th peak point compared with the normal peak point, the greater the risk of abnormality caused by scattering, and the greater the degree of scattering abnormality of the i-th peak point; (n i+1 +n i-1 ) is used to characterize the degree of continuity of the fluctuation from the ith peak point to the left and right adjacent peak points, (n i+1 +n i-1 ) is larger, indicating that the waveform of the i-th peak point is larger, the extension is stronger, and the more likely it is a sudden change peak point caused by scattering, and the corresponding scattering anomaly is greater at the i-th peak point.

[0056] After determining the degree of scattering anomaly, the anomaly threshold is set to 0.8. If the degree of scattering anomaly of any point is greater than or equal to the preset anomaly threshold, the mean value of the reflection intensity between the left adjacent data point and the right adjacent data point of the point is obtained, and the reflection intensity of the point is replaced by the mean value of the reflection intensity. If the degree of scattering anomaly of any point is less than the preset anomaly threshold, the reflection intensity of the point is kept unchanged. Similarly, the degree of scattering anomaly of each crest point and trough point in the spectral signal curve is obtained, and then the reflection intensity of each crest point and trough point is smoothed according to the degree of scattering anomaly, and the smoothed spectral signal curve is obtained, which is recorded as the target spectral signal curve, thereby smoothing out the influence of abnormal signals caused by scattering.

[0057] At this point, the smoothing process of each spectral signal curve is completed, and multiple target spectral signal curves are obtained.

[0058] The curve division module 12 is used to obtain the target spectral signal curve within at least two consecutive preset periods, map all the target spectral signal curves into the same two-dimensional plane, the horizontal axis of the two-dimensional plane is the wavelength, and the vertical axis is the reflection intensity, and divide all the target spectral signal curves in the two-dimensional plane into at least two spectral signal sub-curve sets according to the inflection point of each target spectral signal curve in the two-dimensional plane.

[0059] Considering that the moisture characteristics of general sweet potato tubers are mainly displayed between 1400nm and 1900nm of the spectrum, but when irrigation is just completed, the soil layer above the sweet potato tubers contains a large amount of water, and the water content of the soil particles is relatively high. Before the infrared light contacts the sweet potato tubers, some large soil particles containing water may reflect infrared light to the spectrometer in advance, and they also exist between 1400nm and 1900nm on the spectrometer. As a result, the spectrum of the moisture characteristic band actually monitored is not the performance of the sweet potato tubers, and is mixed with the soil characteristics.

[0060] Therefore, in the embodiment of the present invention, in combination with the water loss characteristics of soil and sweet potato root tubers, the difference in the water loss rate characteristics of soil and sweet potato root tubers is analyzed, and the specific difference is: the soil above the sweet potato root tubers is directly exposed to the air to the soil surface, which will be affected by solar radiation and wind, and the water is lost in large quantities by evaporation, so that the water loss rate is faster after irrigation; and the cells storing water in the sweet potato root tubers will lose water due to the external dry environment or pressure change, and there is a certain water retention capacity in the root tuber cell structure, so when the surrounding soil moisture is still sufficient, the water loss rate of the sweet potato root tubers is low. Correspondingly, after the end of irrigation, as time goes by, in the spectral signal curve collected normally, the moisture in the sweet potato root tubers gradually decreases, forming multiple spectral signal curves with gradually decreasing reflection intensity, and according to the difference in water loss characteristics between soil and sweet potato, in the water characteristic band interval, if there is a spectral signal fluctuation caused by soil reflection, then the different spectral signal curves of the soil are monitored compared to the spectral signal curve fluctuation of the sweet potato root tubers, and the interval of the spectral signal curve of the soil should be larger, and the waveform change degree between the adjacent monitored spectral signal curves is greater.

[0061] Based on the above features, the embodiment of the present invention obtains the target spectral signal curves within at least two consecutive preset periods, and maps all the target spectral signal curves to the same two-dimensional plane. Figure 2 , which is a schematic diagram of a two-dimensional plane, the horizontal axis of the two-dimensional plane is the wavelength A, the vertical axis is the reflection intensity B, and the two-dimensional plane includes target spectral signal curves under multiple monitoring of the target sweet potato root tubers, and different colors represent different target spectral signal curves.

[0062] Although each target spectral signal curve has slight differences in reflection intensity and waveform, the fluctuation trend of each target spectral signal curve is similar, so the position of the inflection point is also similar, and the aggregated target spectral signal curve can be divided into multiple segments through adjacent inflection points, each segment representing a characteristic fluctuation. Specifically, first, the inflection point on each target spectral signal curve is obtained and marked in a two-dimensional plane using the second-order derivative method, wherein the inflection point on the curve is the point on the curve where the concavity and convexity change, that is, the concavity and convexity dividing point of the curve, and the second-order derivative method belongs to the prior art and will not be described in detail here. Then, according to the inflection point of each target spectral signal curve in the two-dimensional plane, all target spectral signal curves in the two-dimensional plane are divided into at least two spectral signal sub-curve sets.

[0063] Among them, the division method is: clustering the inflection points of all target spectral signal curves in the two-dimensional plane to obtain at least two inflection point clustering clusters, obtaining the center of gravity of each inflection point clustering cluster, and drawing a vertical line through each center of gravity according to the position of each center of gravity in the two-dimensional plane. Using the vertical line, all target spectral signal curves in the two-dimensional plane are divided into at least two spectral signal sub-curve sets, that is, the spectral signal sub-curves belonging to the same wavelength range in each target spectral signal curve are grouped into a set, and one spectral signal sub-curve set corresponds to one wavelength range.

[0064] In one embodiment, all the inflection points marked on the two-dimensional plane are clustered and divided using the K-means clustering algorithm to obtain multiple inflection point clusters, one inflection point cluster represents a fluctuation feature, and then the center of gravity in each inflection point cluster is obtained, and according to the position of the center of gravity in each cluster in the two-dimensional plane, a vertical line is drawn through the center of gravity in each cluster to divide all target spectral signal curves in the two-dimensional plane into at least two spectral signal sub-curve sets. Figure 3 , which is a schematic diagram of the division of the target spectral signal curve in the two-dimensional plane, Figure 3 The dotted line in is a vertical line through the centroid of the cluster, corresponding to Figure 3 The spectral signal is divided into 7 sub-curve sets.

[0065] The curve correction module 13 is used to obtain the soil reflection anomaly degree of the corresponding spectral signal sub-curve set according to the difference between each spectral signal sub-curve in each spectral signal sub-curve set, and to correct the reflection intensity of each spectral signal on each target spectral signal curve according to the soil reflection anomaly degree of each spectral signal sub-curve set to obtain a corrected target spectral signal curve.

[0066] After obtaining the spectral signal sub-curve set, the characteristic differences of the water loss rate can be analyzed in sequence by sub-wave segments to obtain the degree of soil reflection anomaly of each spectral signal sub-curve set. Therefore, in the embodiment of the present invention, for any spectral signal sub-curve set, the wavelength interval corresponding to the any spectral signal sub-curve set is obtained, and any wavelength in the wavelength interval is taken as the target wavelength. The absolute value of the difference in reflection intensity corresponding to the target wavelength of each two adjacent spectral signal sub-curves in the any spectral signal sub-curve set is calculated to obtain the cumulative sum of the absolute values ​​of the differences;

[0067] The cumulative sum of the absolute values ​​of the differences corresponding to each wavelength in the wavelength interval is obtained, and the average of the cumulative sum of the absolute values ​​of the differences is obtained as the degree of signal change difference of any spectral signal sub-curve set.

[0068] In one implementation, taking the pth spectral signal sub-curve set as an example, the signal change difference degree of the pth spectral signal sub-curve set is calculated:

[0069]

[0070] Among them, C p Indicates the degree of signal change difference of the pth spectral signal sub-curve set, n p represents the number of wavelengths in the wavelength interval corresponding to the pth spectral signal sub-curve set, m represents the number of spectral signal sub-curves in the pth spectral signal sub-curve set, that is, the number of target spectral signal curves, x i_j represents the emission intensity corresponding to the i-th wavelength on the j-th spectral signal sub-curve in the p-th spectral signal sub-curve set, x i_j+1 represents the emission intensity corresponding to the i-th wavelength on the j+1-th spectral signal sub-curve in the p-th spectral signal sub-curve set, and || represents the absolute value sign.

[0071] It should be noted that Characterizes the overall reflection intensity difference of all spectral signal sub-curves at the same wavelength. The larger the overall reflection intensity difference, the greater the degree of difference in the spectral signal change at this wavelength. Therefore, when the mean of the overall reflection intensity difference of all wavelengths is larger, it means that the difference between adjacent spectral signal sub-curves in the p-th spectral signal sub-curve set is larger, corresponding to the change of the water loss characteristics of the loaded soil in the spectral signal.

[0072] According to the above method for obtaining the signal change difference degree of the pth spectral signal sub-curve set, the signal change difference degree of each spectral signal sub-curve set is obtained respectively, and according to the signal change difference degree of each spectral signal sub-curve set, the soil reflectance anomaly degree of any spectral signal sub-curve set is obtained. The specific obtaining method is:

[0073] The average value of the signal change difference degrees of all spectral signal sub-curve sets is calculated, the absolute value of the difference between the signal change difference degree of any spectral signal sub-curve set and the average value is calculated, recorded as the difference characteristic value, and the product of the difference characteristic value and the signal change difference degree of any spectral signal sub-curve set is normalized to obtain the soil reflectance anomaly degree of any spectral signal sub-curve set.

[0074] In one embodiment, the calculation expression of the soil reflectance anomaly degree of the pth spectral signal sub-curve set is:

[0075]

[0076] Among them, W prepresents the soil reflectance anomaly of the pth spectral signal sub-curve set, norm() represents the normalization function, C p Indicates the degree of signal change difference of the pth spectral signal sub-curve set, It represents the average value of the signal change differences of all spectral signal sub-curves, and || represents the absolute value sign.

[0077] It should be noted that It is used to characterize the difference between the soil reflectance anomaly of the pth spectral signal sub-curve set and the mean of the soil reflectance anomaly of all spectral signal sub-curve sets. The fluctuation difference between the normal spectral signal curves of sweet potato tubers is small and similar, while the fluctuation difference of the spectral signal curve caused by soil reflection is larger, and the difference with the spectral signal curves in other wavelength ranges is more obvious. Therefore, The larger the value of , the more likely the p-th spectral signal sub-curve set is to be disturbed by soil reflection, and the greater the corresponding soil reflection anomaly. At the same time, the greater the difference in signal changes of the p-th spectral signal sub-curve set, the greater the difference in its own changes, and the more likely it is to be disturbed by soil reflection, and the greater the corresponding soil reflection anomaly.

[0078] Similarly, the soil reflection anomaly degree of each spectral signal sub-curve set is obtained, and then the reflection intensity of each spectral signal on each target spectral signal curve is corrected according to the soil reflection anomaly degree of each spectral signal sub-curve set, so as to eliminate the interference caused by soil reflection and improve the spectral signal data of sweet potato tubers to be more real, wherein the correction method is:

[0079] The soil reflection anomaly degree of each of the spectral signal sub-curve sets is compared with a preset soil reflection anomaly degree threshold value. If the soil reflection anomaly degree of any spectral signal sub-curve set is less than the soil reflection anomaly degree threshold value, the reflection intensity of each spectral signal on each spectral signal sub-curve in the spectral signal sub-curve set is kept unchanged;

[0080] If the soil reflection anomaly degree of any spectral signal sub-curve set is greater than or equal to the soil reflection anomaly degree threshold, then the reflection intensity of each spectral signal on each spectral signal sub-curve in the arbitrary spectral signal sub-curve set is corrected to obtain a corrected spectral signal sub-curve set;

[0081] The spectral signal sub-curve in each of the modified spectral signal sub-curve sets is used to replace the corresponding spectral signal sub-curve in each of the target spectral signal curves to obtain each modified target spectral signal curve.

[0082] In one embodiment, the soil reflection anomaly threshold is set to 0.7. If the soil reflection anomaly of any spectral signal sub-curve set is less than 0.7, it means that the spectral signal data of the wavelength interval corresponding to the spectral signal sub-curve set is not affected by soil reflection, and each spectral signal sub-curve in the spectral signal sub-curve set is kept unchanged; on the contrary, if the soil reflection anomaly of any spectral signal sub-curve set is greater than or equal to 0.7, it is considered that the spectral signal data of the wavelength interval corresponding to the spectral signal sub-curve set is affected by soil reflection, and the spectral signal data of each spectral signal sub-curve in the spectral signal sub-curve set needs to be corrected. At this time, each spectral signal sub-curve set is traversed, and each target spectral signal curve is corrected and adjusted according to the traversal result to obtain a corrected target spectral signal curve, that is, a real spectral signal curve excluding soil reflection interference.

[0083] Preferably, the reflection intensity of each spectral signal on each spectral signal sub-curve in the arbitrary spectral signal sub-curve set is corrected to obtain a corrected spectral signal sub-curve set, comprising:

[0084] For any spectral signal on each spectral signal sub-curve in the arbitrary spectral signal sub-curve set, obtain the product of a preset multiple and the degree of soil reflection anomaly of the arbitrary spectral signal sub-curve set, and use the sum of a constant 1 and the product as a correction coefficient for the arbitrary spectral signal, and obtain the corrected reflection intensity of the arbitrary spectral signal according to the product of the correction coefficient and the reflection intensity of the arbitrary spectral signal.

[0085] In one embodiment, due to faster soil moisture loss, the spectral signal curve affected by soil reflection fluctuates less between 1400nm and 1900nm than the spectral signal curve of normal sweet potato tubers. Therefore, the correction needs to increase the reflection intensity of the spectral signal data in the abnormal wavelength band accordingly. Taking the kth spectral signal on any spectral signal sub-curve in the pth spectral signal sub-curve set as an example, the calculation expression for obtaining the corrected reflection intensity of the kth spectral signal is:

[0086] x′ k =x k ×(1+0.2×W p )

[0087] Among them, x′ k represents the corrected reflection intensity of the kth spectral signal, that is, the corrected reflection intensity, x k represents the reflection intensity of the kth spectral signal, that is, the reflection intensity before correction. 1 represents a constant, 0.2 represents a preset multiple, and W p Indicates the degree of soil reflectance anomaly of the pth spectral signal sub-curve set.

[0088] At this point, each target spectral signal curve has been corrected, and a plurality of corrected target spectral signal curves have been obtained.

[0089] The status monitoring module 14 is used to monitor the growth status of the target sweet potato root tubers according to each of the corrected target spectral signal curves.

[0090] Each corrected target spectral signal curve is compared with the standard spectral signal curve during normal growth of sweet potato to obtain the peak significance of each corrected target spectral signal curve. When the peak significance of any corrected target spectral signal curve exceeds the allowable peak significance error range, it means that the moisture growth state of the target sweet potato root tuber after irrigation is abnormal, and it is necessary to check the target sweet potato root tuber in time to see whether there is uneven watering or poor irrigation, and make timely adjustments.

[0091] It should be noted that the focus of the present invention is how to correct the spectral signal curve of the sweet potato root tubers. Monitoring the growth status of the target sweet potato root tubers according to the corrected target spectral signal curve belongs to the prior art and will not be repeated here.

[0092] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A sweet potato root growth status monitoring system based on spectral imaging analysis, characterized in that: The system comprises: A data acquisition module is used to collect infrared spectrum signals of target sweet potato tubers within a preset period, construct a corresponding spectrum signal curve, wherein the horizontal axis of the spectrum signal curve is wavelength, and the vertical axis is reflection intensity, and the spectrum signal curve is smoothed according to the peaks and valleys in the spectrum signal curve to obtain a target spectrum signal curve; A curve division module, used to obtain target spectral signal curves within at least two consecutive preset periods, map all target spectral signal curves to the same two-dimensional plane, the horizontal axis of the two-dimensional plane is the wavelength, and the vertical axis is the reflection intensity, and divide all target spectral signal curves in the two-dimensional plane into at least two spectral signal sub-curve sets according to the inflection point of each target spectral signal curve in the two-dimensional plane; A curve correction module, used for obtaining the soil reflection anomaly degree of the corresponding spectral signal sub-curve set according to the difference between each spectral signal sub-curve in each spectral signal sub-curve set, and correcting the reflection intensity of each spectral signal on each target spectral signal curve according to the soil reflection anomaly degree of each spectral signal sub-curve set to obtain a corrected target spectral signal curve; The status monitoring module is used to monitor the growth status of the target sweet potato root tubers according to each of the corrected target spectral signal curves.

2. The sweet potato root growth status monitoring system based on spectral imaging analysis according to claim 1 is characterized in that: The data acquisition module performs smoothing processing on the spectral signal curve according to the peaks and valleys in the spectral signal curve to obtain a target spectral signal curve, including: Acquire the peak points and the trough points in the spectral signal curve, and for any point among the peak points and the trough points, acquire the degree of scattering anomaly of the any point according to the adjacent data points of the any point on the spectral signal curve; If the scattering abnormality degree of any point is greater than or equal to a preset abnormality degree threshold, then the reflection intensity average between the left adjacent data point and the right adjacent data point of the any point is obtained, and the reflection intensity of the any point is replaced by the reflection intensity average; if the scattering abnormality degree of any point is less than the preset abnormality degree threshold, then the reflection intensity of the any point is kept unchanged; Each of the wave peaks and each of the wave valleys is traversed to obtain a target spectrum signal curve.

3. The sweet potato root growth status monitoring system based on spectral imaging analysis according to claim 2 is characterized in that: The step of obtaining the degree of scattering anomaly of any point according to adjacent data points of any point on the spectral signal curve comprises: Calculate the absolute values ​​of the differences in reflection intensity between any point and its left adjacent data point and right adjacent data point respectively to obtain an average absolute value of the difference, and perform normalization processing on the average absolute value of the difference to obtain the local difference degree of any point; Obtain a left adjacent wave crest point or a left adjacent wave trough point of any point on the spectral signal curve, count the number of left interval data points between any point and the left adjacent wave crest point or the left adjacent wave trough point, obtain the number of right interval data points between any point and its right adjacent wave crest point or the right adjacent wave trough point, and use a preset exponential function to inversely normalize the sum of the number of left interval data points and the number of right interval data points to obtain the degree of fluctuation continuation of any point; The degree of scattering anomaly at any point is obtained according to the degree of local difference at any point and the degree of continuity of the fluctuation.

4. The sweet potato root growth status monitoring system based on spectral imaging analysis according to claim 1 is characterized in that: The curve division module divides all target spectral signal curves in the two-dimensional plane into at least two spectral signal sub-curve sets according to the inflection point of each target spectral signal curve in the two-dimensional plane, including: Cluster the inflection points of all target spectral signal curves in the two-dimensional plane to obtain at least two inflection point clustering clusters, obtain the center of gravity of each inflection point clustering cluster, draw a vertical line through each center of gravity according to the position of each center of gravity in the two-dimensional plane, and use the vertical line to divide all target spectral signal curves in the two-dimensional plane into at least two spectral signal sub-curve sets.

5. The sweet potato root growth status monitoring system based on spectral imaging analysis according to claim 1, characterized in that: The curve correction module obtains the soil reflectance anomaly degree of the corresponding spectral signal sub-curve set according to the difference between each spectral signal sub-curve in each spectral signal sub-curve set, including: For any spectral signal sub-curve set, obtain the wavelength interval corresponding to the any spectral signal sub-curve set, take any wavelength in the wavelength interval as the target wavelength, and respectively calculate the absolute value of the difference in reflection intensity of every two adjacent spectral signal sub-curves in the any spectral signal sub-curve set corresponding to the target wavelength to obtain the cumulative sum of the absolute values ​​of the differences; Obtaining the cumulative sum of absolute values ​​of the differences corresponding to each wavelength in the wavelength interval, and obtaining the mean of the cumulative sum of absolute values ​​of the differences as the degree of signal change difference of any spectral signal sub-curve set; The signal change difference degree of each of the spectral signal sub-curve sets is obtained, and the soil reflectance anomaly degree of any of the spectral signal sub-curve sets is obtained according to the signal change difference degree of each of the spectral signal sub-curve sets.

6. The sweet potato root growth status monitoring system based on spectral imaging analysis according to claim 5, characterized in that: The step of obtaining the soil reflectance anomaly degree of any spectral signal sub-curve set according to the signal change difference degree of each spectral signal sub-curve set comprises: The average value of the signal change difference degrees of all spectral signal sub-curve sets is calculated, the absolute value of the difference between the signal change difference degree of any spectral signal sub-curve set and the average value is calculated, recorded as the difference characteristic value, and the product of the difference characteristic value and the signal change difference degree of any spectral signal sub-curve set is normalized to obtain the soil reflectance anomaly degree of any spectral signal sub-curve set.

7. The sweet potato root growth status monitoring system based on spectral imaging analysis according to claim 1 is characterized in that: The curve correction module corrects the reflection intensity of each spectral signal on each target spectral signal curve according to the soil reflection anomaly degree of each spectral signal sub-curve set to obtain a corrected target spectral signal curve, including: The soil reflection anomaly degree of each of the spectral signal sub-curve sets is compared with a preset soil reflection anomaly degree threshold value. If the soil reflection anomaly degree of any spectral signal sub-curve set is less than the soil reflection anomaly degree threshold value, the reflection intensity of each spectral signal on each spectral signal sub-curve in the spectral signal sub-curve set is kept unchanged; If the soil reflection anomaly degree of any spectral signal sub-curve set is greater than or equal to the soil reflection anomaly degree threshold, then the reflection intensity of each spectral signal on each spectral signal sub-curve in the arbitrary spectral signal sub-curve set is corrected to obtain a corrected spectral signal sub-curve set; The spectral signal sub-curve in each of the modified spectral signal sub-curve sets is used to replace the corresponding spectral signal sub-curve in each of the target spectral signal curves to obtain each modified target spectral signal curve.

8. The sweet potato root growth status monitoring system based on spectral imaging analysis according to claim 7 is characterized in that: The step of correcting the reflection intensity of each spectral signal on each spectral signal sub-curve in the arbitrary spectral signal sub-curve set to obtain a corrected spectral signal sub-curve set includes: For any spectral signal on each spectral signal sub-curve in the arbitrary spectral signal sub-curve set, obtain the product of a preset multiple and the degree of soil reflection anomaly of the arbitrary spectral signal sub-curve set, and use the sum of a constant 1 and the product as a correction coefficient for the arbitrary spectral signal, and obtain the corrected reflection intensity of the arbitrary spectral signal according to the product of the correction coefficient and the reflection intensity of the arbitrary spectral signal.

Images