Assessment method based on crop growth

Abstract

The invention relates to the technical field of intelligent agriculture, in particular to a crop growth evaluation method, which comprises the following steps: acquiring a crop growth image, and preprocessing the image; grid division is carried out on the crop area, and a growth space state matrix is constructed; performing insect pest detection on the grid images by using an insect pest detection model and a disease detection model, and outputting the number of areas of insect pest sub-images and the number of areas of disease sub-images; calculating a first growth index by using the area number of insect pests and diseases; and judging the crop growth state by using the first growth index and a preset threshold. The problem that an existing crop growth assessment method is high in complexity is solved.

Description

Technical Field

[0001] The present invention relates to the field of smart agricultural technology, and in particular to a method for evaluating crop growth. Background Art

[0002] As the global population increases, society's demand for food is growing. How to improve food production and quality is a question that scientists and crop growers have been exploring.

[0003] Smart agriculture is a new agricultural model that optimizes and intelligently manages agricultural production. By analyzing crop growth images through deep learning algorithms, it is possible to identify and monitor crop growth conditions, pests and diseases, etc.

[0004] The patent publication number is CN119888508A. It uses hyperspectral images of crops to calculate the vegetation index of crops, performs initial clustering on hyperspectral image pixels according to the vegetation index, and uses the hyperspectral image pixel where the cluster center is located as the center; calculates the vegetation index distance of the pixel, uses the vegetation index distance and spectral distance to calculate the pixel distance matrix, uses the center and pixel distance matrix to re-cluster the pixels, establishes a correspondence between the initial cluster center and the re-clustering center, calculates the intersection of the pixels of the clusters with corresponding centers in the initial cluster and the re-clustering, determines the dimensionality reduction amplitude based on the intersection, and performs dimensionality reduction on the hyperspectral image; determines the target vegetation index from the vegetation index, uses the target vegetation index and the hyperspectral image after dimensionality reduction to perform semantic segmentation to obtain a crop classification map. This method mainly performs crop classification through image processing, requires a large amount of data set annotation, and the algorithm is relatively complex. Summary of the Invention

[0005] Aiming at the shortcomings of existing methods, the present invention solves the problem of high complexity of existing crop growth assessment methods.

[0006] The technical solution adopted by the present invention is: a method based on crop growth assessment includes the following steps:

[0007] Step 1: Acquire crop growth images and perform image preprocessing;

[0008] As a preferred embodiment of the present invention, image preprocessing includes: grayscale conversion, size normalization, cropping and filling, noise removal, contrast enhancement, and edge and texture enhancement.

[0009] Step 2: Grid the crop area and construct a growth space state matrix;

[0010] As a preferred embodiment of the present invention, grid division is to divide the crop growing area into n1×n2 square blocks of the same area.

[0011] As a preferred embodiment of the present invention, the number of grids is to randomly extract elements from the spatial state matrix.

[0012] Step 3: Use the pest detection model and the disease detection model to detect pests in the grid sub-images, and output the number of areas of the pest sub-images and the disease sub-images;

[0013] Step 4: Calculate the first growth index using the number of areas of pests and diseases;

[0014] As a preferred embodiment of the present invention, the formula for the first growth index is:

[0015]

[0016] where b is the preset pest and disease index, a1 is the number of areas of pests, a2 is the number of areas of diseases, and a3 is the number of areas of pests and diseases.

[0017] Step 5: Use the first growth index and the preset threshold to judge the growth state of the crops.

[0018] As a preferred embodiment of the present invention, Step 5 specifically includes:

[0019] When S1 < T1, it indicates that the crops are growing well;

[0020] When T1 ≤ S1 ≤ T2, it indicates that the crops are growing normally;

[0021] When S1 > T2, it indicates that the crops are growing poorly.

[0022] As a preferred embodiment of the present invention, it further includes: obtaining the soil index of the crop grid; comparing the soil index with the preset soil index to judge the soil health state.

[0023] As a preferred embodiment of the present invention, it further includes: performing field management instruction operations according to the growth state of the crops.

[0024] As a preferred embodiment of the present invention, the crop growth evaluation system based on it includes: a memory for storing instructions executable by a processor; a processor for executing the instructions to implement the crop growth evaluation method.

[0025] As a preferred embodiment of the present invention, a computer-readable medium storing computer program code, the computer program code realizes the crop growth evaluation method when executed by a processor.

[0026] The beneficial effects of the present invention:

[0027] 1. By dividing the crop growing area into multiple square blocks of equal size, it is convenient for precise management of crop planting. The planting plan can be adjusted according to the real-time growth information of each square block, thereby improving the yield and quality of crops.

[0028] 2. By using image detection technology and methods to obtain soil data, it is possible to monitor crops in real time during their growth period, promptly detect pests and diseases and related growth abnormalities, and take relevant prevention and control measures, thereby improving resource utilization and automated management capabilities, and promoting the sustainable development of smart agriculture. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 This is a flow chart of the crop growth assessment method of the present invention. DETAILED DESCRIPTION

[0030] The present invention will be further described below in conjunction with the accompanying drawings and embodiments. This figure is a simplified schematic diagram, which only illustrates the basic structure of the present invention in a schematic manner, and therefore only shows the components related to the present invention.

[0031] like Figure 1 As shown, a method for evaluating crop growth includes the following steps:

[0032] Step 1: Acquire crop growth images and perform image preprocessing;

[0033] Crops such as wheat, rice, corn, etc.;

[0034] Image preprocessing includes: grayscale conversion, size normalization, cropping and padding, noise removal, contrast enhancement, and edge and texture enhancement;

[0035] Step 2: Grid the crop area and construct a growth space state matrix;

[0036] Grid division is to divide the crop growing area into n1×n2 square blocks of equal area;

[0037] The formula of the growth space state matrix is:

[0038]

[0039] The elements in the array represent the square block numbers into which the crop growth area is divided, and record the plane coordinates of the square blocks.

[0040] Randomly extract a elements from F to obtain a grid sub-image. The formula for the number of grids is:

[0041]

[0042] Step 3: Use the pest detection model and the disease detection model to detect pests in the grid sub-images, and output the number of regions of the pest sub-images and the disease sub-images;

[0043] The pest detection model and the disease detection model can adopt the existing YOLOv model;

[0044] Step 4: Calculate the first growth index using the number of regions of pests and diseases;

[0045] The formula for the first growth index is:

[0046]

[0047] where b is the preset pest and disease index, a1 is the number of regions of pests, a2 is the number of regions of diseases, and a3 is the number of regions of pest and diseases.

[0048] Step 5: Use the first growth index and the preset threshold to judge the growth state of the crops;

[0049] When S1 < T1, it indicates that the crops are growing well;

[0050] When T1 ≤ S1 ≤ T2, it indicates that the crops are growing well;

[0051] When S1 > T2, it indicates that the crops are growing poorly;

[0052] where T1 and T2 are the preset first and second thresholds;

[0053] It also includes: obtaining the soil indicators of the crop grid; comparing the soil indicators with the preset soil indicators to judge the soil health state;

[0054] For example: the soil indicators being approximately equal to the preset soil indicators indicates that the soil is healthy; otherwise, the soil health is poor; trigger fertilization and watering operations;

[0055] The acquisition of soil indicators can use soil indicator detection sensors, and the soil indicators include: soil humidity, nutrient content, pH value, etc.

[0056] Using a soil humidity sensor to detect the water content in the soil, including: a resistive sensor that indirectly reflects humidity by measuring soil conductivity; a capacitive sensor that detects moisture through changes in dielectric constant; a frequency domain reflectometer that measures through frequency changes.

[0057] Using a soil nutrient sensor to detect the nutrients in the soil, including: an ion selective electrode (ISE) that detects specific ions (such as NO3 - 、K + 、NH4 +); optical sensors, which estimate nutrient content through near-infrared (NIR) or spectral analysis; and electrochemical sensors, which combine redox reactions to measure organic matter or salt.

[0058] Soil pH sensors are used to detect the acidity and alkalinity of the soil, including glass electrode pH sensors, solid-state pH sensors and composite sensors.

[0059] It also includes: carrying out field management instruction operations according to the growth status of crops;

[0060] If the crop growth status is good, a regular observation instruction is issued through the instruction operation module;

[0061] If the crop growth status is good, the command operation module will issue operations such as spraying pesticides, fertilizing or watering in the corresponding grid;

[0062] If the crop growth status is poor, the command operation module will issue instructions to all grids to spray pesticides, apply fertilizers or water, etc.

[0063] The method of the present invention can obtain the judgment of the growth status of crops through a simple threshold evaluation method, which is simple and effective; and corresponding field management is carried out according to the growth status, effectively improving pests and diseases and increasing crop yields.

[0064] With the above-described preferred embodiments of the present invention as a guide, and with reference to the above description, relevant personnel are fully capable of making various changes and modifications without departing from the technical scope of this invention. The technical scope of this invention is not limited to the contents of the specification and must be determined according to the scope of the claims.

Claims

1. A method for evaluating crop growth, characterized in that: It includes the following steps: Step 1: Obtain the crop growth images and perform image preprocessing; Step 2: Divide the crop area into grids and construct a growth space state matrix; Step 3: Use the pest detection model and disease detection model to detect pests in the grid sub-images, and output the number of areas of the pest sub-images and disease sub-images; Step 4: Calculate the first growth index using the number of areas of pests and diseases; Step 5: Use the first growth index and a preset threshold to judge the growth state of the crops.

2. The method for evaluating crop growth according to claim 1, wherein: The formula for the first growth index is: where b is the preset pest and disease index, a1 is the number of areas of pests, a2 is the number of areas of diseases, and a3 is the number of areas of pests and diseases.

3. The method for evaluating crop growth according to claim 2, wherein: Step 5 specifically includes: When S1 < T1, it indicates that the crops are growing well; When T1 ≤ S1 ≤ T2, it indicates that the crops are growing normally; When S1 > T2, it indicates that the crops are growing poorly; S1 is the first growth index, and T1 and T2 are the preset first and second thresholds.

4. The method for evaluating crop growth according to claim 1, wherein: It also includes: Obtain the soil indicators of the crop grids; compare the soil indicators with the preset soil indicators to judge the soil health state.

5. The method for evaluating crop growth according to claim 1, wherein: It also includes: Perform field management instruction operations according to the crop growth state.

6. The method for evaluating crop growth according to claim 1, wherein: Image preprocessing includes: grayscale conversion, size normalization, cropping and padding, noise removal, contrast enhancement, and edge and texture enhancement.

7. The method for evaluating crop growth according to claim 1, wherein: Grid division is to divide the crop growth area into n1×n2 square blocks with the same area.

8. The method for evaluating crop growth according to claim 1, wherein: The number of grids is to randomly extract elements from the space state matrix.

9. Based on the crop growth assessment system, it is characterized by: It includes: A memory for storing instructions executable by a processor; A processor for executing the instructions to implement the crop growth evaluation method according to any one of claims 1-8.

10. A computer-readable medium storing computer program code, characterized in that The computer program code implements the crop growth evaluation method according to any one of claims 1-8 when executed by the processor.

Images