CN114740004A - A method for root rot detection and localization based on the acquisition of corn hyperspectral spectrum by unmanned aerial vehicle - Google Patents

Abstract

The method for detecting and locating root rot disease based on the acquisition of corn hyperspectral by unmanned aerial vehicle belongs to the field of early prediction technology of agricultural diseases, which can timely and efficiently monitor the corn root rot disease that may occur in the whole process of corn production and management. The present invention establishes a root rot identification model based on the difference in chlorophyll changes of the leaves of corn plants in different periods and different degrees of root rot, and through the root rot identification model, about 14 days before the corn disease plants have no apparent symptoms Correct diagnosis can be made, and the diseased area can be located in the farmland at the same time, which can provide decision-making for early prevention and timely treatment of corn root rot disease, and improve corn yield. The invention has the characteristics of accuracy and speed, can improve the level of agricultural production, reduce the cost of agricultural production management, and improve the yield, quality and benefit of agricultural products.

Description

A method for root rot detection and localization based on the acquisition of corn hyperspectral spectrum by unmanned aerial vehicle

technical field

The invention belongs to the technical field of early prediction of agricultural diseases, and in particular relates to a method for detecting and locating root rot disease based on the collection of corn hyperspectral spectrum by an unmanned aerial vehicle.

Background technique

Corn is one of the main food crops in my country, and its planting area and total output are second only to wheat and rice. Corn is widely used. In addition to eating and configuring high-quality livestock feed, it is also one of the important raw materials for light industry and pharmaceutical industry. Therefore, corn plays an important role in the development of the national economy. However, due to changes in climate, changes in cultivation systems and types The frequent replacement of corn diseases is one of the important factors restricting the development of corn. Therefore, preventing corn diseases has become a key link to ensure the current sustainable increase in corn production. Corn root rot is one of the serious fungal diseases in the seedling stage of maize. It is generally infected at the 2-leaf stage of maize, the roots turn brown at the 4-leaf stage, and the maize leaves show symptoms at the 8-leaf stage, which gradually turn yellow and wither from bottom to top. Due to the strong concealment in the early stage of maize root rot and the late appearance of superficial symptoms, the incidence of the disease in some parts of the country is as high as 80%, which has a great impact on maize yield.

At present, the traditional monitoring of pests and diseases mainly adopts artificial field investigation, and the diagnosis is made based on the form and symptoms of the occurrence and development of the disease. It relies on human sensory judgment, which is not only inefficient, poor in accuracy, but also difficult. It requires the detection personnel to have strong professional skills. Knowledge or experience is difficult to promote on a large scale. There are also field samples for diagnosis through chemical analysis, but this detection method has high requirements on the accuracy of the detected samples and the operator's operating skills, and has high cost, long time, and more damage to the samples. It is also easy to cause environmental damage. Pollution.

SUMMARY OF THE INVENTION

In order to solve the problems existing in the prior art, the present invention provides a method for detecting and locating root rot disease based on the acquisition of corn hyperspectral spectrum by an unmanned aerial vehicle, which can timely and efficiently monitor the corn root that may occur in the whole process of corn production and management. rot disease.

The technical scheme adopted by the present invention to solve the technical problem is as follows:

A method for detecting and locating root rot based on the acquisition of corn hyperspectral by drone, the method includes the following steps:

Step 1: induce 2-leaf stage maize root rot, and collect the hyperspectral reflectance of the diseased maize roots and healthy maize plants;

Step 2: perform first-order differential calculation on the hyperspectral reflectance of the diseased corn plants and healthy corn plants described in Step 1, and select bands with significant differences under different disease degrees as characteristic bands;

Step 3: Calculate the normalized hyperspectral reflectance values of healthy corn plants and diseased corn roots according to the characteristic wavebands described in Step 2, and establish roots according to the normalized hyperspectral reflectance values and the characteristic wavebands. Rot disease identification model;

Step 4: Use the drone to collect the hyperspectral reflectance of maize at different leaf stages in the area to be tested;

Step 5: According to the corn hyperspectral reflectance described in Step 4 and the root rot identification model described in Step 3, the disease condition of the corn in the area to be tested is predicted, the diseased area map is drawn, and the degree of disease occurrence is determined by manual re-examination.

Preferably, the induction of 2-leaf stage corn root rot described in step 1 is achieved by artificial inoculation of pathogens.

Preferably, the diseased corn root is mild disease at the 4-leaf stage and moderate disease at the 6-leaf stage.

Preferably, in step 1, the hyperspectral reflectances of the healthy corn plants and diseased corn roots are collected by a portable spectrometer.

Preferably, the wavelength of the characteristic spectral band is 550 nm to 740 nm as the characteristic band.

Preferably, the root rot identification model includes areas with mild disease, moderate disease and severe disease.

Preferably, the specific steps of the fourth step are: using an unmanned aerial vehicle equipped with a hyperspectral camera to take an orthophoto image of the area to be measured, and collect data.

Preferably, the specific steps of the fourth step further include: setting a route before the UAV takes off, and placing a reflective panel on the ground for radiation calibration and calibration.

The beneficial effects of the present invention are as follows: the present invention establishes a root rot identification model based on the difference of the chlorophyll changes of the leaves of the corn plant at different stages and under different degrees of root rot, and the root rot identification model can be used in the diseased corn plants without The correct diagnosis is made about 14 days before the apparent symptoms, and the diseased area can be located in the farmland at the same time, which can provide decision-making for the early prevention and timely treatment of corn root rot disease, and improve the corn yield. The invention has the characteristics of accuracy and speed, can improve the level of agricultural production, reduce the cost of agricultural production management, and improve the yield, quality and benefit of agricultural products.

Description of drawings

FIG. 1 is a schematic flowchart of the method for detecting root rot and locating based on the acquisition of corn hyperspectral spectrum by an unmanned aerial vehicle according to the present invention.

FIG. 2 is a graph showing the relationship between the hyperspectral wavelength of corn root rot and the corn hyperspectral reflectance in the method for detecting and locating root rot based on the method of collecting corn hyperspectral by unmanned aerial vehicle according to the present invention.

FIG. 3 is a graph showing the relationship between the hyperspectral wavelength in corn root rot and the first-order differential of corn hyperspectral in the method for detecting and locating root rot based on the method of collecting corn hyperspectral by drone according to the present invention.

FIG. 4 is a corn root rot identification model of the method for detecting and locating root rot based on the acquisition of corn hyperspectrum by an unmanned aerial vehicle of the present invention.

Fig. 5 shows the diseased position of corn in the research area of the experimental field in the method for detecting and locating root rot based on the acquisition of corn hyperspectral spectrum by an unmanned aerial vehicle of the present invention.

Detailed ways

The present invention will be further described in detail below with reference to the accompanying drawings and embodiments.

As shown in Figure 1, the method for detecting and locating rot disease based on the acquisition of corn root hyperspectral spectrum by drones includes the following steps:

Step 1: Induce root rot of 2-leaf stage maize by artificial inoculation, and collect hyperspectral reflectance of 4-leaf stage, 6-leaf stage diseased maize and healthy maize plants by a portable spectrometer, as shown in Figure 2.

Step 2: Perform first-order differential calculation on the hyperspectral reflectance of diseased corn plants and healthy corn plants.

where p'(i) is the first-order differential at band i, p(i+1) is the reflectivity of the next sampling band, p(i-1) is the reflectivity of the previous sampling band, and Δp is the wavelength Sampling interval, the results are shown in Figure 3, and the 550nm-740nm band with significant differences in mild, moderate and severe degrees is selected as the characteristic band.

Step 3: Calculate the normalized value of hyperspectral reflectance,

In the formula: z(i) is the normalized value of hyperspectral reflectance at band i, p(i) is the hyperspectral reflectance at band i, m(i) is the envelope value at band i; according to The normalized value of the hyperspectral reflectance and the characteristic bands described in step 2 establish a root rot identification model, and plot the hyperspectral reflectance of mildly diseased corn at the 4-leaf stage, moderately diseased corn at the 6-leaf stage, and healthy corn plants The rate normalized value curve is used to determine the areas of mild patients (I), moderate patients (II), and severe patients (III) in the characteristic bands, as shown in Figure 4.

Step 4: Use a hyperspectral drone to collect the hyperspectral reflectance of corn in the area to be measured, use a drone equipped with a hyperspectral camera to take orthophoto images of the area to be measured, collect data, and set the route before the drone takes off. flight parameters, and a calibration reflective panel is placed on the ground for radiometric calibration.

Step 5: Predict the condition of the corn in the area to be tested according to the rot identification model, determine the location of the disease, compare the spectral data of the area to be tested collected by the drone with the root rot identification model, determine whether the corn is diseased, and draw the disease The location map is used to determine the degree of disease occurrence through manual re-examination.

Example 1: The experimental field of Jilin Agricultural Science and Technology College of Jilin Province was selected as the observation object, and the 4-leaf stage corn hyperspectral data was collected by unmanned aerial vehicle. After analysis and calculation, compared with the corn root rot identification model, there are 2 regions of corn hyperspectral The reflectance curve is in the mild disease area, and the disease occurrence is determined by manual re-examination. As shown in Table 1, the above two areas were determined to be "affected" by manual re-examination, which was consistent with the spectral detection results. The affected areas are shown in Figure 5.

Table 1 Disease situation in different regions

While the basic principles and main features and advantages of the present invention have been shown and described above, it will be apparent to those skilled in the art that the present invention is not limited to the details of the above-described exemplary embodiments, but without departing from the spirit or essential aspects of the present invention. In the case of the characteristic features, the present invention can be implemented in other specific forms. Therefore, the embodiments are to be regarded in all respects as illustrative and not restrictive, and the scope of the invention is to be defined by the appended claims rather than the foregoing description, which are therefore intended to fall within the scope of the claims. All changes within the meaning and scope of the equivalents of , are included in the present invention. Any reference signs in the claims shall not be construed as limiting the involved claim.

In addition, it should be understood that although this specification is described in terms of embodiments, not each embodiment only includes an independent technical solution, and this description in the specification is only for the sake of clarity, and those skilled in the art should take the specification as a whole , the technical solutions in each embodiment can also be appropriately combined to form other implementations that can be understood by those skilled in the art.

Claims (8)

1. the method for detecting root rot and positioning based on the collection of corn hyperspectral by unmanned aerial vehicle, is characterized in that, the method comprises the steps: Step 1: induce 2-leaf stage maize root rot, and collect the hyperspectral reflectance of the diseased maize roots and healthy maize plants; Step 2: perform first-order differential calculation on the hyperspectral reflectance of the diseased corn plants and healthy corn plants described in Step 1, and select bands with significant differences under different disease degrees as characteristic bands; Step 3: Calculate the normalized hyperspectral reflectance values of healthy corn plants and diseased corn roots according to the characteristic wavebands described in Step 2, and establish roots according to the normalized hyperspectral reflectance values and the characteristic wavebands. Rot disease identification model; Step 4: Use the drone to collect the hyperspectral reflectance of maize at different leaf stages in the area to be tested; Step 5: According to the corn hyperspectral reflectance described in Step 4 and the root rot identification model described in Step 3, the disease condition of the corn in the area to be tested is predicted, the diseased area map is drawn, and the degree of disease occurrence is determined by manual re-examination. 2. the method for detecting root rot and positioning based on unmanned aerial vehicle collection corn hyperspectrum according to claim 1, is characterized in that, the induction of 2-leaf stage corn root rot described in step 1 is to utilize artificial inoculation of germs way realized. 3. the method for detecting root rot and positioning based on the collection of corn hyperspectral by unmanned aerial vehicle according to claim 1, it is characterized in that, described sick corn root is 4 leaf stage mild disease and 6 leaf stage moderate disease. patient. 4. the method for detecting root rot and positioning based on the collection of corn hyperspectral by unmanned aerial vehicle according to claim 1, is characterized in that, in step 1, the height of described healthy corn plant, diseased corn root is collected by portable spectrometer. Spectral reflectance. 5 . The method for detecting root rot and locating based on the collection of corn hyperspectrum by an unmanned aerial vehicle according to claim 1 , wherein the wavelength of the characteristic spectrum is 550 nm to 740 nm. 6 . 6. the method for detecting root rot and positioning based on the collection of corn hyperspectral by unmanned aerial vehicle according to claim 1, is characterized in that, described root rot identification model comprises mild disease, moderate disease and severe disease. patient area. 7. the method for detecting root rot and positioning based on the collection of corn hyperspectral by unmanned aerial vehicle according to claim 1, it is characterized in that, the concrete steps of described step 4 are: utilize the unmanned aerial vehicle carrying hyperspectral camera to treat Orthophoto shooting of the survey area and data collection. 8. the method for detecting root rot and positioning based on unmanned aerial vehicle collection corn hyperspectrum according to claim 7, is characterized in that, the concrete step of described step 4 is to further comprise: described unmanned aerial vehicle takes off before setting. Determine the route, and place the reflective panel for radiation calibration and calibration on the ground of the area to be measured.

Images