Method and device for automatically extracting cotton seeds

Abstract

The invention provides a method and device for automatically extracting cotton seeds. The method comprises the following steps of: step one, using green plants and soil color characteristics to carry out background segmentation on colorful images in a cotton seed field; step two, using position characteristics of cotton seed line spacing to carry out cotton seed belt location on the green plants obtained by the background segmentation; step three, using position characteristics of cotton seed row spacing to carry out single-plant cotton seed location and plant counting on the located cotton seed belts; and step four, using shape characteristics of the cotton seeds and weeds to extract the single-plant cotton seeds to obtain a cotton seed image in the field in accordance with the plant number of the cotton seeds. According to the method and device, the quick and automatic extraction of the cotton seeds with high recognition rate can be realized.

Description

technical field [0001] The invention belongs to the technical field of automatic control of precision agricultural machinery equipment, in particular to a method and a device for automatic identification of field cotton seedling information. Background technique [0002] The irrational use of pesticides in my country's agricultural production is common, which has led to serious agricultural ecological environment pollution, and the harm is very serious. One is that the number of times of prevention and control is too high, and pesticides are used excessively, which exceeds 50% in cotton production; the other is that the effective utilization rate of pesticides is low, only 20-30% on field crops, which is far lower than the average level of 50% in developed countries. Therefore, precision agriculture variable spraying technology has become a research hotspot. To realize variable spraying, the first step is to solve the automatic identification of crop diseases, insect pests ...

AI Technical Summary

Problems solved by technology

[0004] 1) Manual monitoring is to use GPS or other positioning systems to manually and automatically record the locations of field crops where diseases, insect pests and weeds have occurred before spraying, and then draw a distribution map. This method is inefficient and labor-intensive , Relying entirely on manual experience, manual monitoring is powerless in the observation of large-scale seedlings

[0005] 2) Although remote sensing monitoring overcomes many disadvantages of manual monitoring, due to the low spatial and spectral resolution of remote sensing images, it is mainly used to identify several pests and weeds that occur in a large area within a certain growth period, resulting in a low recognition rate And low positioning accuracy

The near-ground image monitoring of cotton seedlings usually uses the characteristics of cotton seedlings with red stems to extract cotton seedlings. Due to the problems of plastic film covering, cotton leaf expansion covering cotton seedling stems, and the similar color of soil and cotton seedling stems, color The recognition rate of the method of automatically extracting cotton seedlings is low, and the automatic recognition rate of cotton seedlings of this method is usually lower than 80%

Images