Pea germination rate prediction method and system based on hyperspectral reflectivity

Abstract

The invention provides a pea germination rate prediction method and system based on hyperspectral reflectivity, and relates to the technical field of hyperspectrum, and the method comprises the steps: obtaining the hyperspectral image data of historical peas and the corresponding germination condition; generating a germ recognition coefficient according to the reflectivity of 680nm and 1730nm, and comparing an image germ region with other regions through the coefficient; the reflectivity of the multiple wave bands of the germ area is analyzed to generate a germ activity evaluation coefficient; calculating an average value of the germ activity evaluation coefficients of each pixel point in the germ region to obtain an average activity evaluation coefficient; researching the spatial distribution of the germ area to generate a germ spatial distribution reasonable coefficient; constructing and training a pea germination prediction model by taking the germ spatial distribution reasonable coefficient and the average germ activity evaluation coefficient as input and taking the pea germination condition as a label; certain samples are selected for germination prediction, and the germination rate is calculated. When the germination rate is predicted, unique structures, components and spatial distribution of the peas are considered, so that the prediction result is more accurate.

Description

Technical Field

[0001] The present invention relates to the field of hyperspectral technology, and in particular to a method and system for predicting pea germination rate based on hyperspectral reflectance. Background Art

[0002] The existing methods for detecting the germination rate of pea seeds mainly rely on traditional artificial germination test methods, which usually require culturing pea seeds under specific temperature and humidity conditions for a period of time (usually 5 to 7 days) and calculating the germination rate based on the actual germination situation. Although the results of this method are intuitive, the detection cycle is long, the labor intensity is high, and it cannot meet the needs of rapid detection of large quantities of seeds. In addition, this type of method is destructive to a certain extent and is not non-destructive and real-time. With the development of intelligent and precise agriculture, the use of hyperspectral technology for non-destructive detection of crop seeds has become a research hotspot. Some studies have attempted to use hyperspectral reflectance data to predict the moisture content or vitality of crop seeds, but existing methods generally have problems such as insufficient detection accuracy, poor generalization ability of algorithm models, and inability to accurately distinguish between the germ and non-germ areas of pea seeds.

[0003] In the prior art, publication number CN103636315A discloses an online detection device and method for seed germination rate based on hyperspectrum, including S1 performing hyperspectral image acquisition on seed training samples, and extracting characteristic parameters of the hyperspectral images of the seed training samples in characteristic bands; S2 using traditional methods to test the seed training samples to obtain germination results of the seed training samples; S3 using the characteristic parameters and spectral reflectance values ​​of the hyperspectral images of the seed training samples in characteristic bands as input, and the seed germination results as output, to establish a seed germination rate prediction model based on hyperspectrum; S4 performing hyperspectral image acquisition on seeds to be detected, and using the seed germination rate prediction model to detect, to obtain the germination rate of the seeds to be detected.

[0004] However, the existing technology still has shortcomings. The existing technology only collects high-spectral data of whole seeds and analyzes the overall spectral characteristics. There is basically no comprehensive and detailed analysis of the special internal moisture, composition and spatial distribution of peas. For seeds such as peas with thick seed coats and complex internal structures, embryo activity is the key factor determining the germination rate. The overall spectral signal is easily interfered by the seed coat reflection, affecting the prediction accuracy.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The object of the present invention is to provide a method and system for predicting pea germination rate based on hyperspectral reflectance to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions: A pea germination rate prediction based on hyperspectral reflectance, the specific steps include: 1. A method for predicting pea germination rate based on hyperspectral reflectance, characterized in that the specific steps include: Step 1: Acquire historical hyperspectral image data of peas and corresponding germination conditions; the hyperspectral image data of peas is hyperspectral image data of a single pea, and the corresponding germination conditions include germination and non-germination; Step 2: Calculate the germ recognition coefficient of each pixel point according to the reflectance of peas at wavelengths of 680nm and 1730nm in the hyperspectral image data, and divide the hyperspectral image data of peas into germ areas and other areas according to the germ recognition coefficient; Step 3: Analyze the reflectance of the pea germ region at wavelengths of 970nm, 1450nm and 1940nm in the hyperspectral image data to generate a moisture evaluation coefficient, and analyze the reflectance of the pea germ region at wavelengths of 680nm, 1200nm and 1730nm in the hyperspectral image data to generate a component activity evaluation coefficient; generate a germ activity evaluation coefficient based on the moisture evaluation coefficient and the component activity evaluation coefficient; calculate the average value of the germ activity evaluation coefficients of all pixel points in the pea germ region as the average activity evaluation coefficient; Step 4: Calculate the pea center of the pea in the hyperspectral image data, and calculate the reasonable coefficient of germ spatial distribution according to each pixel point of the pea center and the pea germ area in the hyperspectral image data; use the reasonable coefficient of germ spatial distribution and the average germ activity evaluation coefficient as input, and the pea germination situation as a label to build and train a pea germination prediction model; Step 5: Randomly select N peas from a batch of peas whose germination rate is to be predicted, and calculate the reasonable coefficient of germ spatial distribution and the average germ activity evaluation coefficient of each pea according to steps 1 to 4; input the reasonable coefficient of germ spatial distribution and the average germ activity evaluation coefficient of the randomly selected peas into the pea germination prediction model to obtain the germination situation of the randomly selected peas, and calculate the pea germination rate according to the predicted germination situation.

[0008] Furthermore, the hyperspectral image acquired by the hyperspectral imaging system includes peas and background, and the pea area is manually marked, and the hyperspectral image of the pea area is cropped as the hyperspectral image data of the peas, the hyperspectral imaging system includes a visible light + near-infrared detector and a short-wave infrared detector, wherein the visible light + near-infrared detector can cover the 400-1000nm band, the short-wave infrared detector can cover the 1000-2500nm band, the hyperspectral imaging system can cover the 400-2500nm band, and the wavelength resolution of the hyperspectral imaging system is 1-5nm.

[0009] Furthermore, the specific formula for calculating the germ recognition coefficient is: ; in, is the first The germ recognition coefficient of pixels is is the first The reflectivity of pixels at a wavelength of 680nm is is the first The reflectivity of pixels at a wavelength of 1730nm is is the index of the pixel point of the hyperspectral image data of pea; The specific logic for dividing the hyperspectral image data of peas into the germ area and other areas is as follows: the germ recognition threshold is preset ,Will All pixels of constitute the germ area. All pixels of constitute the other area.

[0010] Furthermore, the specific formula for generating the moisture assessment coefficient is: ; in, The germ region of pea The moisture evaluation coefficient of each pixel, The germ region of pea The reflectivity of pixels at a wavelength of 970nm is The germ region of pea The reflectivity of pixels at a wavelength of 1450nm is The germ region of pea The reflectivity of pixels at a wavelength of 1940nm is is the index of the pixel points in the pea germ area; The specific formula used to generate the component evaluation coefficient is: ; in, The germ region of pea The component evaluation coefficient of each pixel is The germ region of pea The reflectivity of pixels at a wavelength of 680nm is The germ region of pea The reflectivity of pixels at a wavelength of 1200nm is The germ region of pea The reflectivity of each pixel at a wavelength of 1730nm; , and is the weight coefficient, and , ; The specific formula for generating the germ activity evaluation coefficient is: ; in, The germ region of pea Germ activity evaluation coefficient of each pixel.

[0011] Furthermore, the specific formula for calculating the pea center is: ; ; in, The center of the pea. is the first The position of the pixel; The specific formula for generating a reasonable coefficient of germ spatial distribution is: ; in, is the rational coefficient of germ spatial distribution, The pea germ area in the hyperspectral image data is The position of the pixel, is the total number of pixels in the pea germ area, is the index of the pixel point in the pea germ area.

[0012] Furthermore, the specific logic for calculating the pea germination rate is as follows: the number of peas that are germinated in the prediction results is counted, and the number of peas that are germinated in the prediction results is divided by the total number of selected peas to obtain the germination rate; the specific formula for calculating the germination rate is as follows: ; in, is the germination rate, To predict the number of peas with germination status as germinated, is the total number of peas selected.

[0013] The present invention further provides a coal mine supervision system based on video images, the system is used to realize the prediction of pea germination rate based on hyperspectral reflectance, and specifically includes: A data acquisition module, used to obtain historical hyperspectral image data of peas and corresponding germination conditions; the hyperspectral image data of peas is the hyperspectral image data of a single pea, and the corresponding germination conditions include germination and non-germination; A region recognition module is used to calculate the germ recognition coefficient of each pixel point according to the reflectance of peas at wavelengths of 680nm and 1730nm in the hyperspectral image data, and divide the hyperspectral image data of peas into germ regions and other regions according to the germ recognition coefficient; The activity evaluation module is used to analyze the reflectance of the pea germ region at wavelengths of 970nm, 1450nm and 1940nm in the hyperspectral image data to generate a moisture evaluation coefficient, and analyze the reflectance of the pea germ region at wavelengths of 680nm, 1200nm and 1730nm in the hyperspectral image data to generate a component activity evaluation coefficient; generate a germ activity evaluation coefficient according to the moisture evaluation coefficient and the component activity evaluation coefficient; calculate the average value of the germ activity evaluation coefficients of all pixel points in the pea germ region as the average activity evaluation coefficient; The spatial evaluation module is used to calculate the pea center of the pea in the hyperspectral image data, and calculate the reasonable coefficient of germ spatial distribution according to the position of each pixel point in the pea center and the pea germ area of ​​the hyperspectral image data; the reasonable coefficient of germ spatial distribution and the average germ activity evaluation coefficient are used as input, and the pea germination situation is used as a label to build and train a pea germination prediction model; The germination prediction module is used to randomly select N peas from a batch of peas whose germination rate is to be predicted, and calculate the reasonable coefficient of germ spatial distribution and the average germ activity evaluation coefficient of each pea according to steps 1 to 4; input the reasonable coefficient of germ spatial distribution and the average germ activity evaluation coefficient of the randomly selected peas into the pea germination prediction model to obtain the germination situation of the randomly selected peas, and calculate the pea germination rate according to the predicted germination situation.

[0014] Compared with the prior art, the present invention has the following beneficial effects: The present invention constructs a germ recognition coefficient by introducing the reflectivity of the 680nm and 1730nm bands, accurately identifies the germ area in pea seeds, and effectively improves the model's ability to distinguish different tissue structures of peas. Further, by analyzing the reflectivity of 970nm, 1450nm and 1940nm to generate a moisture assessment coefficient, and combining the reflectivity of 680nm, 1200nm and 1730nm to generate a component activity assessment coefficient, a multi-dimensional assessment of the germ vitality state is achieved, which improves the accuracy and scientificity of the model in predicting seed germination rate.

[0015] The present invention also introduces the spatial distribution information in the hyperspectral image data into the prediction model by calculating the reasonable coefficient of the spatial distribution of the germ, comprehensively considering the activity evaluation and spatial distribution of the pea seed germ area, and further improving the adaptability and generalization ability of the model to different varieties and batches of pea seeds. This method realizes the rapid and non-destructive detection of the germination rate of pea seeds, has high prediction accuracy and real-time application capabilities, significantly improves the level of seed quality control and intelligent grading and screening, and meets the needs of intelligent and precise seed management in modern agriculture. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of the overall method flow of the present invention.

[0017] Figure 2 It is a schematic diagram of the overall system structure of the present invention. DETAILED DESCRIPTION

[0018] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0019] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0020] Example: See also Figure 1 , the present invention provides a technical solution: A pea germination rate prediction based on hyperspectral reflectance, the specific steps include: Step 1: Acquire historical hyperspectral image data of peas and corresponding germination conditions; the hyperspectral image data of peas is hyperspectral image data of a single pea, and the corresponding germination conditions include germination and non-germination; The hyperspectral image acquired by the hyperspectral imaging system includes peas and background, and the pea area is manually marked, and the hyperspectral image of the pea area is cut out as the hyperspectral image data of the peas. The hyperspectral imaging system includes a visible light + near-infrared detector and a short-wave infrared detector, wherein the visible light + near-infrared detector can cover the 400-1000nm band, the short-wave infrared detector can cover the 1000-2500nm band, the hyperspectral imaging system can cover the 400-2500nm band, and the wavelength resolution of the hyperspectral imaging system is 1-5nm.

[0021] In a hyperspectral image, each pixel contains complete spectral information. In this embodiment, in a hyperspectral image taken by a hyperspectral imaging system, each pixel contains reflectance information of all bands of 400-2500nm. For the same pixel, the reflectance of all bands of 400-2500nm can be obtained.

[0022] Whiteboard calibration plays a vital role in the processing of hyperspectral reflectance data. It eliminates the influence of light source and instrument through standardization and ensures the accuracy and consistency of data. Whiteboard calibration is an indispensable basic step for building a high-precision and adaptable pea germination rate prediction model.

[0023] Step 2: Calculate the germ recognition coefficient of each pixel point according to the reflectance of peas at wavelengths of 680nm and 1730nm in the hyperspectral image data, and divide the hyperspectral image data of peas into germ areas and other areas according to the germ recognition coefficient; The specific formula for calculating the germ recognition coefficient is: ; in, is the first The germ recognition coefficient of pixels is is the first The reflectivity of pixels at a wavelength of 680nm is is the first The reflectivity of pixels at a wavelength of 1730nm is is the index of the pixel point of the hyperspectral image data of pea; The hyperspectral image data of peas is divided into the germ area and other areas; the specific logic is: preset germ recognition threshold ,Will All pixels of constitute the germ area. All pixels of constitute other areas; Chlorophyll strongly absorbs 680nm. If the chlorophyll content of a pixel is high, it absorbs more light at 680nm, and the reflectivity of 680nm light will be low. The chlorophyll content on the surface of peas is usually small, and the difference in chlorophyll is mainly determined by the internal substances of the peas. Usually, the chlorophyll content of the germ inside the pea is much higher than that of other areas; 1730nm is the absorption area of ​​fatty acid groups. If the fatty acid group content is high, the reflectivity of 1730nm light will be low, and the fatty acid groups in the germ inside the pea are much higher than those in other areas; the germ recognition coefficient generated by coupling the reflectivity of 680nm and 1730nm can well reflect the difference between the germ area and other areas in the hyperspectral image data of peas. The smaller the value, the more the pixel absorbs chlorophyll and fatty acid groups, and the greater the probability of being a germ area; Step 3: Analyze the reflectance of the pea germ region at wavelengths of 970nm, 1450nm and 1940nm in the hyperspectral image data to generate a moisture evaluation coefficient, and analyze the reflectance of the pea germ region at wavelengths of 680nm, 1200nm and 1730nm in the hyperspectral image data to generate a component activity evaluation coefficient; generate a germ activity evaluation coefficient based on the moisture evaluation coefficient and the component activity evaluation coefficient; calculate the average value of the germ activity evaluation coefficients of all pixel points in the pea germ region as the average activity evaluation coefficient; The specific formula used to generate the moisture assessment factor is: ; in, The germ region of pea The moisture evaluation coefficient of each pixel, The germ region of pea The reflectivity of pixels at a wavelength of 970nm is The germ region of pea The reflectivity of pixels at a wavelength of 1450nm is The germ region of pea The reflectivity of pixels at a wavelength of 1940nm is is the index of the pixel points in the pea germ area; The moisture assessment coefficient reflects the activity of pea germ from the moisture level. The smaller the value, the greater the activity of the pea germ and the greater the probability of pea germination. 970nm is the free water absorption peak. The greater its reflectivity, the less free water there is. The pea germ is relatively dry and has low activity, which is not conducive to pea germination. 1940nm reflects the moisture gradient of pea germ. The smaller its reflectivity, the more moisture the pea germ has, and it is not dehydrated or aged, which is conducive to pea germination. 1450nm reflects the absorption of bound water and cell water in pea germ. The smaller its reflectivity, the more bound water and cell water there are in pea germ, the stronger the cell integrity and activity, the better the cell membrane function, which is conducive to pea germination. The influence of 1450nm on the overall moisture assessment is enhanced by means of a logarithmic function.

[0024] The specific formula used to generate the component evaluation coefficient is: ; in, The germ region of pea The component evaluation coefficient of each pixel is The germ region of pea The reflectivity of pixels at a wavelength of 680nm is The germ region of pea The reflectivity of pixels at a wavelength of 1200nm is The germ region of pea The reflectivity of each pixel at a wavelength of 1730nm; , and is the weight coefficient, and , ; The component evaluation coefficient reflects the activity of the germ from the component level. The smaller the value, the greater the activity of the pea germ and the greater the probability of germination. Chlorophyll strongly absorbs 680nm. If the chlorophyll content of the pixel is high, it absorbs more light at 680nm and the reflectivity of 680nm will be low. The chlorophyll content on the surface of peas is usually small, and the difference in chlorophyll is mainly determined by the internal substances of the peas. Usually, the chlorophyll content of the germ inside the peas is much higher than that in other areas; the higher the chlorophyll content of the pea germ, the better the activity of the pea germ and the easier it is to germinate; 1200nm can penetrate thinner cell walls and cytoplasm, and the smaller its reflectivity, the more complete the pea cell structure and the better the tissue uniformity, indicating that the germ cell wall is thin, the substance is rich, and the metabolism is active, which shows that the overall pea seedling activity is high; 1730nm is the absorption area of ​​fatty acid groups. The amount of fatty acid groups can reflect the amount of protein and lipid substances stored in the germ for germination. If the fatty acid group content is high, the reflectivity of 1730nm light will be low. The more protein and lipid substances stored in the germ for germination, the easier it is to germinate. Because the smaller the reflectivity, the more corresponding substances there are, and the greater the probability of germination, the smaller the weight coefficient, the more important the corresponding component. Among the chlorophyll content, pea cell structural integrity and fatty acid groups, the pea cell structural integrity has the greatest impact on pea germination, followed by the impact of fatty acid groups, and the impact of chlorophyll content. Therefore, it is set .

[0025] The specific formula for generating the germ activity evaluation coefficient is: ; in, The germ region of pea The germ activity evaluation coefficient of each pixel reflects the activity of pea germ, and the larger the value, the greater the activity of the pea germ. A single germ activity evaluation coefficient can only reflect the germ activity at a single pixel position. The germ activity evaluation coefficient conducts a comprehensive analysis of the pea germ area to comprehensively reflect the overall activity of the pea germ.

[0026] Step 4: Calculate the pea center of the pea in the hyperspectral image data, and calculate the reasonable coefficient of germ spatial distribution according to the position of each pixel point in the pea center and the pea germ area of ​​the hyperspectral image data; use the reasonable coefficient of germ spatial distribution and the average germ activity evaluation coefficient as input, and the pea germination situation as a label to build and train a pea germination prediction model; The specific formula used to calculate the center of the pea is: ; ; in, The center of the pea. is the first The position of the pixel; The specific formula for generating a reasonable coefficient of germ spatial distribution is: ; in, is the rational coefficient of germ spatial distribution, The pea germ area in the hyperspectral image data is The position of the pixel, is the total number of pixels in the pea germ area, is the index of the pixel points in the pea germ area; The reasonable coefficient of germ spatial distribution reflects the reasonable spatial distribution of pea germs inside peas. The smaller the value, the more reasonable the spatial distribution, and the more conducive to pea germination. is the average distance between the pixel points in the pea germ area and the center of the pea. For peas, the sizes of their internal germs usually do not vary much. The closer the distance to the center, the more reasonable the spatial distribution.

[0027] The pea germination prediction model adopts a feedforward neural network, with the reasonable coefficient of germ spatial distribution and the average germ activity evaluation coefficient as input, and the corresponding pea germination situation as a label. The existing technology can be used to train the pea germination prediction model, specifically including: input layer, hidden layer, output layer and activation function. The input layer is responsible for receiving the reasonable coefficient of germ spatial distribution and the average germ activity evaluation coefficient; the hidden layer is used to process the data of the reasonable coefficient of germ spatial distribution and the average germ activity evaluation coefficient; it is composed of multiple layers, each layer contains 4 time nodes, and the time node of each hidden layer is connected to the previous layer through a weight, which is used to input the reasonable coefficient of germ spatial distribution and the average germ activity evaluation coefficient. The theoretical coefficient and the average germ activity evaluation coefficient are used for feature abstraction and nonlinear transformation; the ReLu activation function is used to introduce nonlinear relationships so that the model can fit complex feature relationships; an independent neuron is set in the output layer, which is responsible for converting the local and high-level feature representations extracted by the hidden layer for outputting the pea germination situation; the root mean square error loss function is adopted; the input data is calculated once through the network to obtain the output result, the loss function is calculated according to the predicted value and the true value, the gradient of the loss function for each weight and bias is calculated by the chain rule, and the weights and biases of the network are updated using the gradient descent algorithm to minimize the loss function.

[0028] Step 5: Randomly select N peas from a batch of peas whose germination rate is to be predicted, and calculate the reasonable coefficient of germ spatial distribution and the average germ activity evaluation coefficient of each pea according to steps 1 to 4; input the reasonable coefficient of germ spatial distribution and the average germ activity evaluation coefficient of the randomly selected peas into the pea germination prediction model to obtain the germination situation of the randomly selected peas, and calculate the pea germination rate according to the predicted germination situation.

[0029] The specific logic for calculating the pea germination rate is: count the number of peas that are germinated in the prediction results, and divide the number of peas that are germinated in the prediction results by the total number of selected peas to obtain the germination rate; the specific formula for calculating the germination rate is: ; in, is the germination rate, To predict the number of peas with germination status as germinated, is the total number of peas selected.

[0030] See also Figure 2 The present invention further provides a coal mine supervision system based on video images, the system is used to realize the prediction of pea germination rate based on hyperspectral reflectance, and specifically includes: A data acquisition module, used to obtain historical hyperspectral image data of peas and corresponding germination conditions; the hyperspectral image data of peas is the hyperspectral image data of a single pea, and the corresponding germination conditions include germination and non-germination; The region recognition module is used in the hyperspectral image data. The reflectivity of peas at wavelengths of 680nm and 1730nm is used to calculate the germ recognition coefficient of each pixel point. The hyperspectral image data of peas is divided into the germ region and other regions by the germ recognition coefficient. The activity evaluation module is used to analyze the reflectance of the pea germ region at wavelengths of 970nm, 1450nm and 1940nm in the hyperspectral image data to generate a moisture evaluation coefficient, and analyze the reflectance of the pea germ region at wavelengths of 680nm, 1200nm and 1730nm in the hyperspectral image data to generate a component activity evaluation coefficient; generate a germ activity evaluation coefficient according to the moisture evaluation coefficient and the component activity evaluation coefficient; calculate the average value of the germ activity evaluation coefficients of all pixel points in the pea germ region as the average activity evaluation coefficient; The spatial evaluation module is used to calculate the pea center of the pea in the hyperspectral image data, and calculate the reasonable coefficient of the spatial distribution of the germ according to each position of the pixel point in the pea center and the germ area of ​​the pea in the hyperspectral image data; the reasonable coefficient of the spatial distribution of the germ and the average germ activity evaluation coefficient are used as input, and the pea germination situation is used as a label to build and train the pea germination prediction model; The germination prediction module is used to randomly select N peas from a batch of peas whose germination rate is to be predicted, and calculate the reasonable coefficient of germ spatial distribution and the average germ activity evaluation coefficient of each pea according to steps 1 to 4; input the reasonable coefficient of germ spatial distribution and the average germ activity evaluation coefficient of the randomly selected peas into the pea germination prediction model to obtain the germination situation of the randomly selected peas, and calculate the pea germination rate according to the predicted germination situation.

[0031] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0032] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0033] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0034] The above is only a specific implementation method of the present application, but the protection scope of the present application is not limited thereto. Any technical personnel familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be covered by the protection scope of the present application.

Claims

1. A pea germination rate prediction based on hyperspectral reflectance, characterized in that: The specific steps include: Step 1: Acquire historical hyperspectral image data of peas and corresponding germination conditions; the hyperspectral image data of peas is hyperspectral image data of a single pea, and the corresponding germination conditions include germination and non-germination; Step 2: Calculate the germ recognition coefficient of each pixel point according to the reflectance of peas at wavelengths of 680nm and 1730nm in the hyperspectral image data, and divide the hyperspectral image data of peas into germ areas and other areas according to the germ recognition coefficient; Step 3: Analyze the reflectance of the pea germ region at wavelengths of 970nm, 1450nm and 1940nm in the hyperspectral image data to generate a moisture evaluation coefficient, and analyze the reflectance of the pea germ region at wavelengths of 680nm, 1200nm and 1730nm in the hyperspectral image data to generate a component activity evaluation coefficient; generate a germ activity evaluation coefficient based on the moisture evaluation coefficient and the component activity evaluation coefficient; calculate the average value of the germ activity evaluation coefficients of all pixel points in the pea germ region as the average activity evaluation coefficient; Step 4: Calculate the pea center of the pea in the hyperspectral image data, and calculate the reasonable coefficient of germ spatial distribution according to the position of each pixel point in the pea center and the pea germ area of ​​the hyperspectral image data; use the reasonable coefficient of germ spatial distribution and the average germ activity evaluation coefficient as input, and the pea germination situation as a label to build and train a pea germination prediction model; Step 5: Randomly select N peas from a batch of peas whose germination rate is to be predicted, and calculate the reasonable coefficient of germ spatial distribution and the average germ activity evaluation coefficient of each pea according to steps 1 to 4; input the reasonable coefficient of germ spatial distribution and the average germ activity evaluation coefficient of the randomly selected peas into the pea germination prediction model to obtain the germination situation of the randomly selected peas, and calculate the pea germination rate according to the predicted germination situation.

2. The method for predicting pea germination rate based on hyperspectral reflectance according to claim 1, characterized in that: The hyperspectral image acquired by the hyperspectral imaging system includes peas and background, and the pea area is manually marked, and the hyperspectral image of the pea area is cut out as the hyperspectral image data of the peas. The hyperspectral imaging system includes a visible light + near-infrared detector and a short-wave infrared detector, wherein the visible light + near-infrared detector can cover the 400-1000nm band, the short-wave infrared detector can cover the 1000-2500nm band, the hyperspectral imaging system can cover the 400-2500nm band, and the wavelength resolution of the hyperspectral imaging system is 1-5nm.

3. The pea germination rate prediction based on hyperspectral reflectance according to claim 2, characterized in that: The specific formula for calculating the germ recognition coefficient is: ； in, is the first The germ recognition coefficient of pixels is is the first The reflectivity of each pixel at a wavelength of 680nm, is the first The reflectivity of pixels at a wavelength of 1730nm is is the index of the pixel point of the hyperspectral image data of pea; The specific logic for dividing the hyperspectral image data of peas into the germ area and other areas is as follows: the germ recognition threshold is preset ,Will All pixels of constitute the germ area. All pixels of constitute the other area.

4. The method for predicting pea germination rate based on hyperspectral reflectance according to claim 2, characterized in that: The specific formula used to generate the moisture assessment factor is: ； in, The germ region of pea The moisture evaluation coefficient of each pixel, The germ region of pea The reflectivity of pixels at a wavelength of 970nm is The germ region of pea The reflectivity of pixels at a wavelength of 1450nm is The germ region of pea The reflectivity of pixels at a wavelength of 1940nm is is the index of the pixel points in the pea germ area; The specific formula used to generate the component evaluation coefficient is: ； in, The germ region of pea The component evaluation coefficient of each pixel is The germ region of pea The reflectivity of pixels at a wavelength of 680nm is The germ region of pea The reflectivity of pixels at a wavelength of 1200nm is The germ region of pea The reflectivity of each pixel at a wavelength of 1730nm; , and is the weight coefficient, and , ; The specific formula for generating the germ activity evaluation coefficient is: ； in, The germ region of pea Germ activity evaluation coefficient of each pixel.

5. The method for predicting pea germination rate based on hyperspectral reflectance according to claim 2, characterized in that: The specific formula used to calculate the center of the pea is: ； ； in, The center of the pea. is the first The position of the pixel; The specific formula for generating a reasonable coefficient of germ spatial distribution is: ； in, is the rational coefficient of germ spatial distribution, The hyperspectral image data shows the pea germ region. The position of the pixel, is the total number of pixels in the pea germ area, is the index of the pixel point in the pea germ area.

6. The method for predicting pea germination rate based on hyperspectral reflectance according to claim 1, characterized in that: The specific logic for calculating the pea germination rate is: the number of peas with germination status in the randomly selected peas predicted by statistics is divided by the total number of peas selected to obtain the germination rate; the specific formula for calculating the germination rate is: ； in, is the germination rate, To predict the number of peas with germination status as germinated, is the total number of peas selected.

7. A coal mine supervision system based on video images, characterized in that: The system is used to realize the prediction of pea germination rate based on hyperspectral reflectance as described in any one of claims 1 to 6, and specifically comprises: A data acquisition module, used to obtain historical hyperspectral image data of peas and corresponding germination conditions; the hyperspectral image data of peas is the hyperspectral image data of a single pea, and the corresponding germination conditions include germination and non-germination; A region recognition module is used to calculate the germ recognition coefficient of each pixel point according to the reflectance of peas at wavelengths of 680nm and 1730nm in the hyperspectral image data, and divide the hyperspectral image data of peas into germ regions and other regions according to the germ recognition coefficient; The activity evaluation module is used to analyze the reflectance of the pea germ region at wavelengths of 970nm, 1450nm and 1940nm in the hyperspectral image data to generate a moisture evaluation coefficient, and analyze the reflectance of the pea germ region at wavelengths of 680nm, 1200nm and 1730nm in the hyperspectral image data to generate a component activity evaluation coefficient; generate a germ activity evaluation coefficient according to the moisture evaluation coefficient and the component activity evaluation coefficient; calculate the average value of the germ activity evaluation coefficients of all pixel points in the pea germ region as the average activity evaluation coefficient; The spatial evaluation module is used to calculate the pea center of the pea in the hyperspectral image data, and calculate the reasonable coefficient of germ spatial distribution according to the position of each pixel point in the pea center and the pea germ area of ​​the hyperspectral image data; the reasonable coefficient of germ spatial distribution and the average germ activity evaluation coefficient are used as input, and the pea germination situation is used as a label to build and train a pea germination prediction model; The germination prediction module is used to randomly select N peas from a batch of peas whose germination rate is to be predicted, and calculate the reasonable coefficient of germ spatial distribution and the average germ activity evaluation coefficient of each pea according to steps 1 to 4; input the reasonable coefficient of germ spatial distribution and the average germ activity evaluation coefficient of the randomly selected peas into the pea germination prediction model to obtain the germination situation of the randomly selected peas, and calculate the pea germination rate according to the predicted germination situation.

Images