Hydroponic flower flowering stage flower grade evaluation method based on deep neural network

Abstract

The invention relates to a hydroponic flower flowering stage flower grade evaluation method based on a deep neural network. The method comprises the steps: designing a hardware system, and configuringthe position of a camera; processing the proportional relation; performing recognition and image segmentation on the top view and the side view of the flower by using a region-based mask convolutional neural network to obtain a contour map and a corolla block diagram of the plant; and calculating the numerical values of four indexes which comprises the plant height, the crown diameter, the flower coverage degree and the flower uniformity degree through the obtained contour map and the corresponding pixel points. The flower grading system based on the deep neural network has the advantages that compared with a traditional idea depending on manual judgment to solve problems, the flower grading system based on the deep neural network can conduct automatic judgment and evaluation through a computer, the flower grading efficiency is greatly improved, meanwhile, differences caused by manual labor are reduced, and universality is achieved. Meanwhile, the process of continuously contacting flowers in the traditional grading evaluation is avoided, and the possibility of damaging the flowers is greatly reduced.

Description

technical field [0001] The invention relates to the field of flower grade evaluation, in particular to a deep neural network-based flower grade evaluation method for hydroponic flowers in flowering stage. Background technique [0002] In recent years, with the rapid development of my country's economy and the continuous improvement of people's living standards, people's demand for life diversity and green environmental protection is increasing. As a novel type of ornamental plants, hydroponic flowers have attracted more and more attention. and favored. my country's flower industry is booming, and its planting area and output both rank first in the world. Although my country is a big country in flower production, it is not a powerful country, and its products are still at the bottom of the value chain. [0003] Generally speaking, flower production can be divided into two stages, the first part is the cultivation of small seedlings, and the second part is the cultivation of l...

AI Technical Summary

Problems solved by technology

However, due to the high price of directly imported foreign grading equipment and the differences with my country's grading standards, it does not meet the requirements of my country's flower grading, so it is necessary to develop my country's own flower grading system

Images