Measurement Method of Plant Phenotypic Parameters Based on Image Deep Learning

Abstract

This article applies deep learning and electromechanical technology to plant phenotype measurement. First, an electromechanical device is designed to collect plant phenotype images, which solves the difficulty of collecting deep learning training data. The data set required for deep learning model training for plant phenotype detection is made by an automated method. This paper takes the Lactuca sativa plant image as an example and uses the ASM-based data enhancement method to solve the problem of insufficient image data of Lactuca sativa leaf pests and effectively avoid the phenomenon of overfitting. The plant image recognition method based on deep learning proposed breaks through the limitations of plant local feature recognition, gets rid of the limitation of highly specialized data collection, lowers the threshold of plant image recognition, and has advantages in recognition speed and accuracy. This method requires a large amount of training data. In the future, we can explore the collection of massive plant pictures from the Internet as a training set to achieve rapid iteration and optimization of the model.

Research advance in phenotype detection robots for agriculture and forestry

“…Phenotype detection robots are replacing traditional phenotype equipment and have attracted more attention worldwide. And this definition helps to refine the work of plant phenotype with the intersection of agriculture and computer [4,[26][27][28][29][30] .…”

“…The American Society of Robotics and the United Nations Organization for Standardization define a robot as a programmable, multi-functional manipulator or a specialized system that can be changed and programmed by a computer to perform different tasks. Robots are widely used in agricultural production and other fields [1][2][3][4] .…”

“…Researchers have built camera control equipment to achieve the acquisition of phenotype data, for example, carrying environmental sensors on mechanical trellises to obtain real-time information on plant growth environment; carrying RGB cameras on agricultural tractors to obtain images of plant canopies; carrying camera platforms on gliders to obtain large-scale group-scale overhead images of farmland, etc. [3,4,8,17] These data can help researchers quickly understand the plant growth condition so that they can respond to unexpected situations in the cultivation process in time. The recent development of machine learning algorithms and big data technologies since the 2010s has increased the intelligence of agricultural robots (Figure 1).…”

A Custom Backbone UNet Framework with DCGAN Augmentation for Efficient Segmentation of Leaf Spot Diseases in Jasmine Plant

“…Te scarcity of suitable datasets poses a signifcant challenge in the development of CNN-based detection algorithms capable of detecting various stages of jasmine plant leaf spot disease. In the past, several segmentation and morphological methods have been reported for grapes and other leaves [17][18][19]. However, there is a need for a semantic segmentation method specifcally designed to extract the leaf spot features of jasmine plants.…”

Method for the real-time detection of tomato ripeness using a phenotype robot and RP-YolactEdge

“…This research indicates that non-destructive methods for evaluating fruit ripeness have become a prominent area of study in precision agriculture within controlled environments. The adoption of non-destructive data acquisition techniques offers advantages such as reduced experimental costs and shortened research cycles [6][7][8] . However, traditional nondestructive approaches for tomato ripeness detection often rely on labor-intensive manual selection and judgment [9][10][11] .…”