CN114858726A - Chlorophyll content determination method, system, device and storage medium - Google Patents

Abstract

The application discloses a chlorophyll content determination method, a system, a device and a storage medium. The method comprises the steps of establishing a multispectral imaging system; acquiring original data of the blade to be detected in different wave bands through a multispectral imaging system; performing black and white correction on the original data to obtain correction data; extracting the region of interest of the correction data to obtain region of interest data; carrying out spectral processing on the data of the region of interest to obtain spectral characteristic data and spectral index data; and inputting the spectral characteristic data and the spectral index data into a chlorophyll content determination model to obtain the chlorophyll content of the leaf to be measured. The system comprises an imaging system module, an acquisition module, a correction module, an area-of-interest module and the like. By using the method, the chlorophyll content of the leaves can be rapidly detected, so that nondestructive large-scale detection is facilitated, and meanwhile, the accuracy of a detection result is facilitated to be improved. The method and the device can be widely applied to the technical field of machine measurement.

Description

A kind of chlorophyll content determination method, system, device and storage medium

technical field

The present application relates to the technical field of machine measurement, in particular to a method, system, device and storage medium for measuring chlorophyll content.

Background technique

At present, the common methods for determination of chlorophyll content mainly include direct measurement method and indirect measurement method. Among them, the direct measurement method is usually an invasive measurement method, which causes damage to plants, and the process is complicated, which cannot meet the needs of large-scale real-time online detection. The indirect measurement method usually cannot directly reflect the chlorophyll content level of the whole leaf, or there are problems of expensive equipment and slow aging.

SUMMARY OF THE INVENTION

The purpose of this application is to solve one of the technical problems existing in the prior art at least to a certain extent.

Therefore, the purpose of the present invention is to provide a fast and reliable method, system, device and storage medium for measuring chlorophyll content.

In order to achieve the above technical purpose, the technical solutions adopted in the embodiments of the present application include:

On the one hand, the embodiments of the present application provide a method for measuring chlorophyll content, comprising the following steps:

The chlorophyll content determination method of the embodiment of the present application establishes a multi-spectral imaging system, and adjusts the parameters of the multi-spectral imaging system; the multi-spectral imaging system includes a MEMS chip-based multi-spectral camera, a ring light source, a stage and a camera obscura, The stage is used to place the blade to be tested; the multi-spectral imaging system collects the original data of the blade to be tested in different wavelength bands; black and white correction is performed on the original data to obtain correction data; Extracting the region of interest to obtain data of the region of interest; performing spectral processing on the region of interest data to obtain spectral characteristic data and spectral index data; inputting the spectral characteristic data and the spectral index data into a chlorophyll content determination model , to obtain the chlorophyll content of the leaves to be tested. By using the above method, the chlorophyll content of leaves can be quickly detected, which is conducive to realizing non-destructive large-scale detection, and at the same time, is conducive to improving the accuracy of the determination results.

In addition, according to the chlorophyll content determination method of the above-mentioned embodiment of the present application, it can also have the following additional technical features:

Further, the chlorophyll content determination method of the embodiment of the present application further comprises the following steps;

Further, in an embodiment of the present application, the collection of raw data of the leaf to be tested in different wavelength bands by the multispectral imaging system includes:

The raw data of the leaves to be tested in 10 different wavebands are collected by the multispectral imaging system, wherein the central wavelengths of the 10 wavebands are: 713nm, 736nm, 759nm, 782nm, 805nm, 828nm, 851nm, 874nm, 897nm and 920nm .

Further, in an embodiment of the present application, the chlorophyll content determination model is trained through the following steps:

obtaining the chlorophyll data of the leaf to be tested;

The chlorophyll data, the spectral characteristic data and the spectral index data are input into the chlorophyll content determination model for training, and the trained chlorophyll content determination model is obtained.

Further, in an embodiment of the present application, the obtaining of the chlorophyll data of the leaf to be tested includes:

Obtain the chlorophyll data of 6 areas on the left and right sides of the root position of the leaf to be measured, wherein the chlorophyll data of each area is obtained by taking an average value after 3 measurements.

Further, in an embodiment of the present application, after the black-and-white correction is performed on the original data to obtain correction data, the method further includes:

performing grayscale processing on the correction data to obtain grayscale data;

performing smooth filtering on the grayscale data to obtain smooth data;

Threshold segmentation processing is performed on the smoothed data to obtain mask data.

Further, in an embodiment of the present application, performing spectral processing on the data of the region of interest to obtain spectral characteristic data and spectral index data, including:

performing multivariate scatter correction processing on the data of the region of interest to obtain scatter data;

Performing standard normal variable transformation processing on the scattering data to obtain optical path data;

Performing Savitzky-Golay smooth derivation processing on the optical path data to obtain spectral characteristic data;

According to the spectral characteristic data and the preset calculation formula, spectral index data is obtained.

Further, in an embodiment of the present application, establishing a multispectral imaging system and adjusting parameters of the multispectral imaging system includes:

Adjust the distance between the ring light source and the blade to be measured, and adjust the distance between the multispectral camera based on the MEMS chip and the blade to be measured, so that the blade to be measured is located in the multispectral camera based on the MEMS chip the center of the field of view;

The exposure and gain values of the MEMS chip-based multispectral camera are adjusted.

On the other hand, the embodiment of the present application proposes a chlorophyll content determination system, comprising:

The imaging system module is used to establish a multi-spectral imaging system and adjust the parameters of the multi-spectral imaging system; the multi-spectral imaging system includes a multi-spectral camera based on a MEMS chip, a ring light source, a stage and a camera obscura. The table is used to place the blade to be tested;

an acquisition module, configured to acquire raw data of the leaf to be measured in different wavelength bands through the multispectral imaging system;

a correction module for performing black and white correction on the original data to obtain correction data;

a region of interest module, configured to perform a region of interest extraction operation on the correction data to obtain region of interest data;

a spectral feature module for performing spectral processing on the data of the region of interest to obtain spectral feature data and spectral index data;

The determination module is used for inputting the spectral characteristic data and the spectral index data into the chlorophyll content determination model to obtain the chlorophyll content of the leaves to be measured.

On the other hand, the embodiment of the present application provides a chlorophyll content determination device, comprising:

at least one processor;

at least one memory for storing at least one program;

When the at least one program is executed by the at least one processor, the at least one processor is caused to implement any one of the above-mentioned chlorophyll content determination methods.

On the other hand, an embodiment of the present application provides a storage medium, in which a processor-executable program is stored, and the processor-executable program, when executed by the processor, is used to realize any one of the above-mentioned determination of chlorophyll content method.

The embodiments of the present application can quickly detect the chlorophyll content of leaves, which is conducive to realizing non-destructive large-scale detection, and at the same time, is conducive to improving the accuracy of the determination results.

Description of drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the accompanying drawings of the embodiments of the present application or the related technical solutions in the prior art are introduced below. It should be understood that the drawings in the following introduction are only In order to facilitate and clearly express some embodiments of the technical solutions of the present application, for those skilled in the art, other drawings can also be obtained from these drawings without creative efforts.

1 is a schematic flowchart of an embodiment of a method for measuring chlorophyll content provided by the application;

Fig. 2 is the schematic flow chart of another embodiment of the chlorophyll content determination method provided by the application;

3 is a schematic flow chart of an embodiment of a chlorophyll content determination system provided by the application;

4 is a schematic structural diagram of another embodiment of the chlorophyll content determination system provided by the application;

FIG. 5 is a schematic structural diagram of an embodiment of the device for measuring chlorophyll content provided by the present application.

Detailed ways

The following describes in detail the embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, but should not be construed as a limitation on the present application. The numbers of the steps in the following embodiments are only set for the convenience of description, and the sequence between the steps is not limited in any way, and the execution sequence of each step in the embodiments can be adapted according to the understanding of those skilled in the art Sexual adjustment.

Chlorophyll is the main pigment for plants to carry out photosynthesis, and it is also an important part of synthesizing plant leaf nitrogen. The content of chlorophyll can reflect the photosynthesis ability of plants and the nutritional status and growth status of vegetation. Therefore, the accurate and rapid determination of chlorophyll content in plant leaves has important guiding significance for agricultural fertilization and crop growth monitoring.

At present, the determination methods of chlorophyll content mainly include direct measurement method and indirect measurement method. The direct measurement method generally uses organic solvents such as acetone or ethanol to extract chlorophyll, and then uses a spectrophotometer to measure the absorbance value of the chlorophyll extract at the maximum absorption wavelength, and the Lambert-Beer law can be used to calculate the content of each pigment in the extract. . Indirect measurement methods mainly include chlorophyll meter method and spectral index method. The chlorophyll meter method refers to the use of a portable chlorophyll content analyzer to determine the relative amount of current chlorophyll in leaves by measuring the difference in optical concentration of leaves at two wavelengths (650nm and 940nm). The spectral index method refers to the use of the light absorption characteristics of chlorophyll in different bands, with the help of various spectral equipment, such as hyperspectral cameras, multispectral cameras, etc., to obtain the reflectance information of plant leaves in different bands, and then through a variety of reflectance combinations, The chlorophyll vegetation index is formed, and then a quantitative regression model is established to invert the chlorophyll content.

The above common chlorophyll content determination methods all have some problems. Spectrophotometry is an invasive measurement method, which causes damage to plants and has a complicated process, which cannot meet the needs of large-scale real-time online detection. The chlorophyll meter method requires the chlorophyll meter to be in contact with the leaves, which is not suitable for high-throughput detection, and the chlorophyll meter adopts point-touch measurement, and the read value is only the chlorophyll content value at the contact point of the instrument probe, which cannot intuitively reflect the entire Chlorophyll content levels in leaves. The spectral index method can realize non-contact, non-destructive measurement, and the measurement is rapid, and can realize the visualization of the distribution of chlorophyll content in plant leaves. However, hyperspectral equipment is expensive, the data collection speed is slow, and it contains a lot of overlapping information, which is difficult to interpret. Multi-spectral equipment can select the research band range according to several characteristic bands absorbed by chlorophyll, which is highly targeted. In addition, the multispectral camera broadens the band range and has more spectral and image information than traditional RGB three-channel digital images. By extracting the image and spectral information of multi-spectral feature bands, the chlorophyll content of leaves can be quantitatively detected to provide guidance for crop growth.

However, multi-lens multispectral cameras have problems such as difficult lens switching, optical parallax, and high cost; multi-camera, beam separation, area array CCD and Bayer filter multispectral cameras have extensive bandwidth and low spatial accuracy. And other issues.

The method and system for measuring chlorophyll content according to the embodiments of the present application will be described in detail below with reference to the accompanying drawings. First, the method for measuring chlorophyll content according to the embodiments of the present application will be described with reference to the accompanying drawings.

Referring to FIG. 1 , a method for measuring chlorophyll content is provided in the embodiment of the present application. The method for measuring chlorophyll content in the embodiment of the present application can be applied to a terminal, a server, or a terminal or a server. software, etc. The terminal may be a tablet computer, a notebook computer, a desktop computer, etc., but is not limited thereto. The server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud service, cloud database, cloud computing, cloud function, cloud storage, network service, cloud communication, intermediate Cloud servers for basic cloud computing services such as software services, domain name services, security services, CDNs, and big data and artificial intelligence platforms. The method for measuring chlorophyll content in the embodiments of the present application mainly includes the following steps:

S110: Establish a multi-spectral imaging system, and adjust parameters of the multi-spectral imaging system; the multi-spectral imaging system includes a MEMS chip-based multi-spectral camera, a ring light source, a stage and a camera obscura, and the stage is used for placing leaves to be tested;

S120: Collect raw data of the leaf to be tested in different wavelength bands through the multispectral imaging system;

S130: Perform black and white correction on the original data to obtain correction data;

S140: Perform a region-of-interest extraction operation on the correction data to obtain region-of-interest data;

S150: Perform spectral processing on the data of the region of interest to obtain spectral characteristic data and spectral index data;

S160: Input the spectral characteristic data and the spectral index data into a chlorophyll content determination model to obtain the chlorophyll content of the leaf to be measured.

Optionally, in the method for measuring chlorophyll content in the embodiments of the present application, the collection of raw data of the leaves to be measured in different wavelength bands by the multispectral imaging system includes:

The raw data of the leaves to be tested in 10 different wavebands are collected by the multispectral imaging system, wherein the central wavelengths of the 10 wavebands are: 713nm, 736nm, 759nm, 782nm, 805nm, 828nm, 851nm, 874nm, 897nm and 920nm .

Optionally, in the method for measuring chlorophyll content in the embodiments of the present application, the model for measuring chlorophyll content is trained through the following steps:

obtaining the chlorophyll data of the leaf to be tested;

The chlorophyll data, the spectral characteristic data and the spectral index data are input into the chlorophyll content determination model for training, and the trained chlorophyll content determination model is obtained.

Optionally, in the method for measuring chlorophyll content in the embodiments of the present application, the obtaining of the chlorophyll data of the leaf to be measured includes:

Obtain the chlorophyll data of 6 areas on the left and right sides of the root position of the leaf to be measured, wherein the chlorophyll data of each area is obtained by taking an average value after 3 measurements.

Optionally, in the method for determining chlorophyll content in the embodiments of the present application, the black and white correction is performed on the original data, and after the corrected data is obtained, the method further includes:

performing grayscale processing on the correction data to obtain grayscale data;

performing smooth filtering on the grayscale data to obtain smooth data;

Threshold segmentation processing is performed on the smoothed data to obtain mask data.

Optionally, in the method for determining chlorophyll content in the embodiments of the present application, performing spectral processing on the data of the region of interest to obtain spectral characteristic data and spectral index data, including:

performing multivariate scatter correction processing on the data of the region of interest to obtain scatter data;

Performing standard normal variable transformation processing on the scattering data to obtain optical path data;

Performing Savitzky-Golay smooth derivation processing on the optical path data to obtain spectral characteristic data;

According to the spectral characteristic data and the preset calculation formula, spectral index data is obtained.

Optionally, in the method for determining chlorophyll content in the embodiments of the present application, the establishment of a multi-spectral imaging system and the adjustment of parameters of the multi-spectral imaging system include:

Adjust the distance between the ring light source and the blade to be measured, and adjust the distance between the multispectral camera based on the MEMS chip and the blade to be measured, so that the blade to be measured is located in the multispectral camera based on the MEMS chip the center of the field of view;

The exposure and gain values of the MEMS chip-based multispectral camera are adjusted.

Optionally, in the method for measuring chlorophyll content in the embodiment of the present application, the collection of raw data of the leaf to be measured in different wavelength bands by the multispectral imaging system includes: a lens of the MEMS chip-based multispectral camera A black opaque lens cover is placed in front; the dark background of the MEMS chip-based multispectral camera is collected, that is, the data generated by the dark current inside the camera; a Spectralon whiteboard is placed next to the blade to be tested.

The chlorophyll content determination method proposed in this application, wherein, MEMS (Micro-Electro Mechanical System), that is, micro-electro-mechanical system, is a high-speed micro-machining technology that integrates mechanical parts, electronic circuits, sensors, and actuators on a circuit board. Value-added components, whose internal structures are generally in the order of micrometers or even nanometers, have the advantages of small size and high integration. The multi-spectral imaging system based on MEMS chip realizes the selection of specific wavelength by applying a specific voltage on the MEMS filter. Compared with other multi-spectral imaging technologies, it has the advantages of small size, higher precision, lower cost, acquisition The advantages of faster data speed and so on.

The key technology of multispectral imaging lies in the spectroscopic system. Multispectral cameras based on MEMS technology are completely different from other multispectral cameras in spectroscopic technology. The filter wheel type multispectral camera captures multi-channel spectral images by rotating the filter in the filter wheel installed in front of the sensor or the lens. Customization is expensive. The multispectral filter array (MSFA) type camera extends the Bayer filter array to the multispectral filter array, and combines the demosaicing technology to achieve single-sensor imaging. The disadvantage is that the crosstalk in the actual band may be relatively high, which affects the overall spectral sensitivity and pixel-related noise parameters. , and the accuracy of spectral reconstruction, in addition, it is more difficult to perform multispectral demosaicing of multispectral filter arrays. The beam splitter type multispectral camera uses a beam splitter to split light. The disadvantage is that there are multiple cameras in the system, which is bulky and expensive. The beam splitter will cause light intensity loss and require high-intensity illumination. The MEMS filter is mainly based on the principle of Fabry-Perot optical cavity. Through voltage changes, the distance between the upper and lower mirrors of the Fabry-Perot cavity is precisely controlled, and the variable optical cavity between the mirrors produces structural interference. achieve wavelength tuning.

In some possible implementations, referring to the multispectral imaging system shown in FIG. 3 , it mainly includes a data acquisition module and a data processing module. The data acquisition module mainly includes a camera obscura 350 , a MEMS chip-based multispectral camera 310 , a ring light source 320 , and a stage 340 , wherein the blade to be tested 330 is placed on the stage. The data processing module is mainly a computer and supporting software 360 for controlling the camera. The acquisition module and the data processing module are connected through a transmission line 370 . During measurement, the camera is controlled to measure by operating the computer software interface. The measured data is transmitted to the computer in real time through the transmission line for subsequent analysis. In some possible embodiments, the MEMS chip-based small multi-spectral camera can capture images in 10 different wavelength bands, and the central wavelengths are: 713nm, 736nm, 759nm, 782nm, 805nm, 828nm, 851nm, 874nm, 897nm, 920nm. In the range of 690-935nm, MEMS technology has the best stability, highest precision and lowest cost for wavelength tuning; in addition, for most green plants, chlorophyll has a certain absorption intensity in the range of 690-935nm. Therefore, the 10 band values in the range 690-935nm are suitable for most green plant leaves. It can be understood by those skilled in the art that the present application does not limit the specific selection of the frequency band. For example, in the range of 690-935nm, some bands can be added on the basis of these 10 narrow bands; or on the basis of these 10 narrow bands, not limited to the range of 690-935nm, some bands can be added, Thus broadening the measurement band range.

In some possible embodiments, referring to Figure 2, the assay method of the present application is achieved by the following steps:

Step 210, establishing a multispectral imaging system, and adjusting the parameters of the imaging system;

Step 220, using the multispectral imaging system to collect leaf data;

Step 230, manually measure the chlorophyll data of the leaves;

In step 240, due to the internal electronics of the camera sensor, the camera has a base signal. If the camera is used under different temperatures or different integration times, the base signal will change. Furthermore, when performing multispectral measurements, the intensity and spectrum of the light source used are critical. Only when the light conditions are clear can the information of the actual leaves to be tested can be obtained. Therefore, in order to eliminate the influence of environment and illumination changes on the collected data, it is necessary to perform black and white correction. According to the data obtained in steps 220 and 230, a preset formula is used to perform black and white correction on the pictures of each band. Since the image contains the background in addition to the leaf to be tested, it is necessary to extract the area where the leaf to be tested is located in the image. In addition, in order to avoid the influence of leaf rhizomes, 3 rectangular areas were extracted from the left and right sides of the leaf root, a total of 6 areas, as regions of interest (ROI). Then the spectral reflectance in the ROI area is averaged as the reflectance of the leaves in this band, and then the spectral index is obtained by combining the reflectances of different bands, and the spectral index and the actual chlorophyll value are regressed to obtain the chlorophyll quantitative prediction model. The chlorophyll content distribution of the whole leaf was then visualized. In the follow-up, the chlorophyll content can be predicted only by taking multispectral images of the leaves to be tested.

In some possible implementations, the step 210 includes: using a transmission line to connect the multi-spectral system to the computer; fixing the blade to be measured in the center of the stage, and to avoid interference from background reflections, the blade to be measured is padded with black at the bottom Diffuser plate; adjust the distance between the ring light source, the multispectral camera and the leaf to be tested, so that the leaf to be tested is located in the center of the field of view of the multispectral camera; adjust the exposure of the multispectral camera by observing the real-time image of the leaf to be tested in the software interface and gain values until the image is at its sharpest, making sure that all bands are not too dark or overexposed.

In some possible implementations, the step 220 includes: turning on the light source, the multispectral camera and the supporting computer software; covering the multispectral camera lens with a black opaque lens cover, and collecting the dark background of the multispectral camera, that is, The data generated by the dark current inside the camera; a standard Spectralon whiteboard is placed next to the blade to be tested, and certain bands to be captured can be manually selected, and 10 bands are captured by default, that is, 10 images of different bands are captured for each blade , the central wavelengths are: 713nm, 736nm, 759nm, 782nm, 805nm, 828nm, 851nm, 874nm, 897nm, 920nm. Finally, select the data saving path, click Collect, and the camera can collect the data in about 1s.

In some possible implementations, the step 230 includes: removing the leaves to be tested, and for each leaf, selecting 3 areas on the left and right sides of the leaf root, 6 areas in total, and using SPAD-502 to measure the chlorophyll content The chlorophyll content of 6 areas was measured by the instrument. In order to reduce the accidental error in the test process, each area was measured 3 times, and the average value of the 3 times was taken as the chlorophyll content value of the area, and the average value of the chlorophyll content in all areas was calculated. as the chlorophyll content of the whole leaf.

In some possible implementation manners, the step 240 includes: the raw data collected by the camera is I ₀ , the dark current data is I _b , and the whiteboard data is I _w , firstly performing black and white correction on the raw data according to formula (1), The corrected data is I.

An image with the largest contrast among the 10 images in step 220 is selected for grayscale, and its pixel value is normalized to a grayscale range of [0, 255], which is convenient for subsequent processing. Perform smooth filtering to filter out image noise. Then perform threshold segmentation, that is, set a threshold, the pixel value in the image whose pixel value is greater than the threshold value is set to 255, and the pixel value less than the threshold value is set to 0. Simple threshold method, Adaptive threshold, Otsu threshold method, etc., get a mask whose pixel value is not 0 only in the leaf area. Then perform image frame selection. First, set a pure black image of the same size as the original image, in which the pixel value is 0. Select 3 areas on each side of the leaf root, set the size and position of the rectangular frame, and set these The pixel value in the area is adjusted to 255, which is used as ROI, and then this image is bitwise ANDed with the above-mentioned mask whose pixel value is not 0 only in the leaf area to obtain a mask with only 6 rectangular areas. By performing a bitwise AND operation with the 10-band images, you can get all images whose pixel value is not 0 only in the rectangular area. Among them, each leaf frame selects 3 areas on the left and right sides of the leaf root, 6 areas in total, respectively corresponding to the 6 areas measured by the chlorophyll content analyzer in step 230. The average reflectance of all pixels in a certain band in the 6 ROI regions is extracted as the reflectance of this band. Spectral preprocessing methods such as multivariate scattering correction (MSC), standard normal variable transformation (SNV), and Savitzky-Golay smooth derivation were used to obtain the spectral features after preprocessing, respectively. MSC and SNV are mainly used to eliminate the effects of surface scattering and optical path variation on diffuse reflectance spectra. Savitzky-Golay smooth derivation can amplify spectral features, resolve overlapping peaks, and improve spectral resolution. Spectral indices were calculated according to Table 1. where R[λ] represents the spectral reflectance at the center wavelength λ.

Table 1

Taking the preprocessed spectral features, spectral indices, spectral features + spectral indices as independent variables, respectively, using support vector regression (SVR), partial least squares regression (PLSR), multiple linear regression (MLR), convolutional neural network ( CNN) and other algorithms to build regression models. According to the coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE) and other evaluation indicators to select the best independent variables and model combination. Collect the multispectral data of the new sample, and then use the best model for prediction after the above black and white correction, ROI extraction, spectral feature extraction and spectral index extraction. According to the reflectivity of the leaves in different regions, the chlorophyll content value was obtained by using the model, and finally the chlorophyll content distribution map of the entire leaf was visualized.

Next, a chlorophyll content determination system according to an embodiment of the present application is described with reference to the accompanying drawings.

FIG. 4 is a schematic structural diagram of a system for measuring chlorophyll content according to an embodiment of the present application.

The system specifically includes:

The imaging system module 410 is used to establish a multi-spectral imaging system and adjust the parameters of the multi-spectral imaging system; the multi-spectral imaging system includes a multi-spectral camera based on a MEMS chip, a ring light source, an object stage and a camera obscura. The stage is used to place the blade to be tested;

a collection module 420, configured to collect raw data of the leaf to be measured in different wavelength bands through the multispectral imaging system;

A correction module 430, configured to perform black and white correction on the original data to obtain correction data;

A region of interest module 440, configured to perform a region of interest extraction operation on the correction data to obtain region of interest data;

A spectral feature module 450, configured to perform spectral processing on the data of the region of interest to obtain spectral feature data and spectral index data;

The determination module 460 is configured to input the spectral characteristic data and the spectral index data into a chlorophyll content determination model to obtain the chlorophyll content of the leaves to be measured.

It can be seen that the contents in the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments. same.

5 , the embodiment of the present application provides a chlorophyll content determination device, including:

at least one processor 510;

at least one memory 520 for storing at least one program;

When the at least one program is executed by the at least one processor 510, the at least one processor 510 is caused to implement the chlorophyll content determination method.

In the same way, the contents in the above method embodiments are all applicable to the present device embodiments, the specific functions implemented by the present device embodiments are the same as the above method embodiments, and the beneficial effects achieved are the same as those achieved by the above method embodiments. Also the same.

The embodiment of the present application further provides a computer-readable storage medium, in which a program executable by the processor 510 is stored, and when the program executable by the processor 510 is executed by the processor 510, the program is used to execute the above-mentioned method for measuring chlorophyll content.

Similarly, the contents in the above method embodiments are all applicable to the present storage medium embodiments, the specific functions implemented by the present storage medium embodiments are the same as the above method embodiments, and the beneficial effects achieved are the same as those achieved by the above method embodiments. The beneficial effects are also the same.

In some alternative implementations, the functions/operations noted in the block diagrams may occur out of the order noted in the operational diagrams. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality/operations involved. Furthermore, the embodiments presented and described in the flow diagrams of the present application are provided by way of example in order to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of the various operations are altered and in which sub-operations described as part of larger operations are performed independently.

Furthermore, although the application is described in the context of functional modules, it should be understood that, unless stated to the contrary, one or more of the functions and/or features may be integrated in a single physical device and/or software module or one or more functions and/or features may be implemented in separate physical devices or software modules. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary for understanding the present application. Rather, given the attributes, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of such modules will be within the routine skill of the engineer. Accordingly, those skilled in the art, using ordinary skill, can implement the present application as set forth in the claims without undue experimentation. It is also understood that the specific concepts disclosed are illustrative only and are not intended to limit the scope of the application, which is to be determined by the appended claims along with their full scope of equivalents.

The functions, if implemented in the form of software functional units and sold or used as independent products, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including Several programs are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes .

The logic and/or steps represented in flowcharts or otherwise described herein, for example, may be considered an ordered listing of executable programs for implementing the logical functions, and may be embodied in any computer-readable medium, For use with program execution systems, apparatuses or devices (such as computer-based systems, systems including processors, or other systems that can fetch programs from and execute programs from program execution systems, apparatuses, or devices), or in conjunction with these program execution systems, apparatuses or equipment. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport the program for use by or in connection with the program execution system, apparatus, or apparatus.

More specific examples (non-exhaustive list) of computer readable media include the following: electrical connections with one or more wiring (electronic devices), portable computer disk cartridges (magnetic devices), random access memory (RAM), Read Only Memory (ROM), Erasable Editable Read Only Memory (EPROM or Flash Memory), Fiber Optic Devices, and Portable Compact Disc Read Only Memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program may be printed, as the paper or other medium may be optically scanned, for example, followed by editing, interpretation, or other suitable medium as necessary process to obtain the program electronically and then store it in computer memory.

It should be understood that various parts of this application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable program execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented by any one or a combination of the following techniques known in the art: Discrete logic circuits, application specific integrated circuits with suitable combinational logic gates, Programmable Gate Arrays (PGA), Field Programmable Gate Arrays (FPGA), etc.

In the above description of the present specification, reference to the description of the terms "one embodiment/example", "another embodiment/example" or "certain embodiments/examples" etc. means the description in conjunction with the embodiment or example. A particular feature, structure, material, or characteristic is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

Although the embodiments of the present application have been shown and described, those of ordinary skill in the art will appreciate that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the present application, The scope of the application is defined by the claims and their equivalents.

The above is a specific description of the preferred implementation of the application, but the application is not limited to the described embodiments, and those skilled in the art can also make various equivalent deformations or replacements under the premise of not violating the spirit of the application, These equivalent modifications or substitutions are all included within the scope defined by the claims of the present application.

Claims (10)

1. A chlorophyll content measuring method is characterized by comprising the following steps:

establishing a multispectral imaging system, and adjusting parameters of the multispectral imaging system; the multispectral imaging system comprises a multispectral camera based on an MEMS chip, an annular light source, an object stage and a dark box, wherein the object stage is used for placing a blade to be detected;

acquiring original data of the blade to be detected in different wave bands through the multispectral imaging system;

performing black and white correction on the original data to obtain correction data;

extracting the region of interest of the correction data to obtain region of interest data;

carrying out spectrum processing on the data of the region of interest to obtain spectral characteristic data and spectral index data;

and inputting the spectral characteristic data and the spectral index data into a chlorophyll content determination model to obtain the chlorophyll content of the leaf to be measured.

2. The method for measuring chlorophyll content according to claim 1, wherein the acquiring raw data of the leaf to be measured at different wavelength bands by the multispectral imaging system comprises:

acquiring original data of the blade to be detected in 10 different wave bands through the multispectral imaging system, wherein the central wavelength of the 10 wave bands is as follows: 713nm, 736nm, 759nm, 782nm, 805nm, 828nm, 851nm, 874nm, 897nm and 920 nm.

3. The chlorophyll content measurement method according to claim 1, wherein the chlorophyll content measurement model is trained by:

acquiring chlorophyll data of the leaf to be detected;

and inputting the chlorophyll data, the spectral characteristic data and the spectral index data into a chlorophyll content determination model for training to obtain the trained chlorophyll content determination model.

4. The method for measuring the chlorophyll content according to claim 3, wherein the obtaining of the chlorophyll data of the leaf to be measured comprises:

and acquiring chlorophyll data of 6 areas on the left side and the right side of the position of the blade root of the blade to be measured, wherein the chlorophyll data of each area is acquired in an averaging mode after 3 times of measurement.

5. The method for measuring a chlorophyll content according to claim 1, wherein the step of performing black-and-white correction on the raw data to obtain corrected data further comprises:

carrying out gray scale processing on the correction data to obtain gray scale data;

performing smooth filtering on the gray data to obtain smooth data;

and performing threshold segmentation processing on the smooth data to obtain mask data.

6. The method for measuring chlorophyll content according to claim 1, wherein the spectral processing of the data of the region of interest to obtain spectral feature data and spectral index data comprises:

performing multivariate scattering correction processing on the data of the region of interest to obtain scattering data;

performing standard normal variable transformation processing on the scattering data to obtain optical path data;

carrying out Savitzky-Golay smooth derivation processing on the optical path data to obtain spectral characteristic data;

and obtaining spectral index data according to the spectral characteristic data and a preset calculation formula.

7. The method for determining chlorophyll content according to claim 1, wherein said establishing a multispectral imaging system, and adjusting parameters of said multispectral imaging system comprises:

adjusting the distance between the annular light source and the blade to be detected, and adjusting the distance between the multispectral camera based on the MEMS chip and the blade to be detected so that the blade to be detected is positioned in the center of the field range of the multispectral camera based on the MEMS chip;

adjusting exposure and gain values of the MEMS chip based multispectral camera.

8. A chlorophyll content measurement system, comprising:

the imaging system module is used for establishing a multispectral imaging system and adjusting parameters of the multispectral imaging system; the multispectral imaging system comprises a multispectral camera based on an MEMS chip, an annular light source, an object stage and a dark box, wherein the object stage is used for placing a blade to be detected;

the acquisition module is used for acquiring the original data of the blade to be detected in different wave bands through the multispectral imaging system;

the correction module is used for performing black and white correction on the original data to obtain correction data;

the region-of-interest module is used for extracting a region of interest from the correction data to obtain region-of-interest data;

the spectral characteristic module is used for carrying out spectral processing on the data of the region of interest to obtain spectral characteristic data and spectral index data;

and the measuring module is used for inputting the spectral characteristic data and the spectral index data into a chlorophyll content measuring model to obtain the chlorophyll content of the leaf to be measured.

9. A chlorophyll content measurement device, comprising:

at least one processor;

at least one memory for storing at least one program;

when executed by the at least one processor, the at least one program causes the at least one processor to implement the chlorophyll content determining method according to any one of claims 1 to 7.

10. A computer-readable storage medium in which a program executable by a processor is stored, characterized in that: the processor-executable program, when executed by a processor, is for implementing the chlorophyll content determination method according to any one of claims 1 to 7.

Images