Bionic Technology and Deep Learning in Agricultural Engineering: Current Status and Future Prospects

Chunlei Tu,Xingsong Wang,Jie Li,Jinxia Li,Cheng Shen

doi:10.3844/ajbbsp.2021.217.231

Abstract

As one of the most important production activity of mankind, agriculture plays an important role in social development. With the development of science and technology, agricultural technology has constantly been explored and researched. By learning and imitating the characteristics of creatures in nature, bionic technology has been applied to the improvement of agricultural machinery and farm implements. In recent years, as an extension of bionic technology, machine vision and deep learning have been widely used in agricultural production. The application of bionic technology and deep learning in agricultural engineering are reviewed in this study. In traditional agricultural engineering, many bionic farming tools were developed to reduce soil resistance and multiple bionic cutting cutters were designed to improve work efficiency and save energy. Machine vision and neural networks were widely used in crop classification, sorting, phenological period recognition and navigation. Deep learning methods can promote the intelligentization of agricultural engineering and has obvious advantages in crop classification, disease and pest identification, growth status evaluation and autonomous robots. Agricultural engineering that integrates bionic technology, machine vision and deep learning will develop toward more automation and intelligence.

Highlights

Agriculture, as one driving force of human development, is the foundation for supporting social stability
This paper systematically introduces the application status of bionic technology, machine vision, neural network and deep learning in agricultural engineering and considers and prospects the future development of bionic technology and deep learning
The bionic technology has played an important role in promoting the agricultural development

Summary

Introduction

Agriculture, as one driving force of human development, is the foundation for supporting social stability. (Zhang et al, 2014) proposed a hybrid classifier that combines the chaos artificial bee colony algorithm and the feedforward neural network, which extracted color, texture and shape features to recognize 18 categories of fruit images, with a recognition accuracy of 89.1%. Fuentes et al (2017) presented deep-learning-based approach to detect diseases and pests (Fig. 9) in tomato plants using images captured in-place by camera devices with various resolutions, with three detectors: Faster R-CNN, R-FCN, SSD and propose a method for local and global class annotation and data augmentation to increase the accuracy and reduce the number of false positives during training.

Results

Conclusion