Corn lodging area extraction system and method based on maximum likelihood method

Abstract

The invention provides a corn lodging area extraction system and method based on a maximum likelihood method. The lodging area can be simply and quickly extracted. The system comprises an collection unit, a preprocessing unit, a calculation unit, a classification unit and an evaluation unit, wherein the collection unit, the preprocessing unit, the calculation unit, the classification unit and theevaluation unit are connected in sequence; the method comprises the steps that an unmanned aerial vehicle is used for carrying a multispectral sensor to collect field image data of a test area; preprocessing the acquired field image data to obtain a corn canopy multispectral image; calculating textural features and series vegetation index information of lodging corn and normal corn in the corn canopy multispectral image; selecting mean value characteristics of three red, green and near-infrared wave bands, combining with five proper classification characteristics of a ratio vegetation index and a triangular vegetation index, using a maximum likelihood method to supervise and classify the images, and extracting a corn lodging area; and verifying the precision of the classification model through field measurement data.

Description

technical field [0001] The invention relates to the field of ground observation and crop phenotype extraction based on drone images, and in particular to a system and method for extracting corn lodging area based on maximum likelihood method. Background technique [0002] Corn is one of the main food crops grown in my country. Lodging often occurs during the growth of corn. It is a common agricultural disaster. There are many reasons for corn lodging. The impact of disastrous weather and the lodging resistance of corn varieties maximum. Studies have shown that the physiological functions of corn such as roots, stems, and leaves are damaged to varying degrees after lodging. In China, the yield of corn with light lodging is reduced by 5% to 10%, and the yield of corn with severe lodging is reduced by 30% to 50%. Lower corn lodging also increases the difficulty of mechanical harvesting. Therefore, after corn lodging occurs, failure to obtain lodging information in time will af...

AI Technical Summary

Problems solved by technology

The manual survey method requires staff to observe, measure and count crop lodging information on the spot. This method is time-consuming, laborious, and inefficient, and is only suitable for small-scale crop lodging investigations; It shows different texture differences and also has different spectral reflectance. The remote sensing image method can distinguish ground objects by analyzing these differences.

This method can obtain a large area of ​​corn remote sensing images at one time, and the efficiency is much higher than that of the manual method. However, there are still some problems in the survey method based on remote sensing: the image acquisition is greatly affected by the weather, and cloudy, rainy and snowy weather will seriously affect the mapping; The reentry cycle to a fixed location is relatively long, and it cannot be guaranteed that the image of the research area can be fully acquired at one time

Images