This book, consisting of 8 chapters, describes the state-of-the-art technological progress and applications of unmanned aerial vehicles (UAVs) in precision agriculture. It focuses on the UAV application in agriculture, such as crop disease detection, mid-season yield estimation, crop nutrient status, and high-throughput phenotyping. Different from individual papers focusing on a specific application, this book provides a holistic view for readers with a wide range of subjects. In addition to researchers in the areas of plant science, plant pathology, breeding, engineering, it is also intended for undergraduates and graduates who are interested in imaging processing, artificial intelligence in agriculture, precision agriculture, agricultural automation, and robotics.
Author(s): Zhao Zhang, Hu Liu, Ce Yang, Yiannis Ampatzidis, Jianfeng Zhou, Yu Jiang
Series: Smart Agriculture, 2
Publisher: Springer
Year: 2022
Language: English
Pages: 137
City: Singapore
Contents
1 Applications of UAVs and Machine Learning in Agriculture
1.1 Introduction
1.2 Types of UAVs
1.3 Examples of UAV-Based Agricultural Applications
1.4 Artificial Intelligence and Machine Learning
1.5 Conclusion
References
2 Robot Operating System Powered Data Acquisition for Unmanned Aircraft Systems in Digital Agriculture
2.1 Introduction
2.2 ROS-Based Data Acquisition System
2.2.1 Basic Concepts and Components in ROS
2.2.2 Connecting with Other UAS Components
2.2.3 Examples for Representative Sensors
2.3 A Case Study for Industrial Hemp Phenotyping
2.3.1 UAS Data Acquisition System
2.3.2 Plant Materials and Experimental Design
2.3.3 Data Acquisition and Ground-Truth Measurements
2.3.4 Data Processing Pipeline for Extracting Morphological and Vegetation Traits
2.3.5 Measurement Accuracy
2.4 Discussion
2.5 Summary
References
3 Unmanned Aerial Vehicle (UAV) Applications in Cotton Production
3.1 Introduction
3.1.1 Precision Agriculture Technology in Agricultural Production
3.1.2 UAV-Based Remote Sensing (RS) for Crop Monitoring
3.1.3 UAV Imagery Data Processing Pipeline
3.2 UAV Systems in Cotton Production
3.2.1 Field Management for Cotton Production
3.2.2 Cotton Emergence Assessment
3.2.3 Cotton Growth Monitoring Using UAV-Based RS
3.2.4 Cotton Yield Estimation
3.3 Summary
References
4 Time Effect After Initial Wheat Lodging on Plot Lodging Ratio Detection Using UAV Imagery and Deep Learning
4.1 Introduction
4.2 Materials and Methods
4.2.1 Experimental Field and Data Collection
4.2.2 Data Pre-Processing and Auto Dataset Generation
4.2.3 Handcrafted Features
4.2.4 Deep Features
4.2.5 Classifier
4.3 Results and Discussion
4.3.1 Deep Learning Model Selection for Deep Feature Extraction
4.3.2 Comparison of Handcrafted and Deep Features
4.4 Conclusion
References
5 UAV Mission Height Effects on Wheat Lodging Ratio Detection
5.1 Introduction
5.2 Materials and Methods
5.2.1 Experimental Field and Data Collection
5.2.2 Data Pre-Processing and Dataset Generation
5.2.3 Machine Learning Algorithm
5.2.4 Deep Learning
5.3 Results and Discussion
5.3.1 Machine Learning Classification Results
5.3.2 Deep Learning Results
5.3.3 Comparison of ML and DL
5.4 Conclusion
References
6 Wheat-Net: An Automatic Dense Wheat Spike Segmentation Method Based on an Optimized Hybrid Task Cascade Model
6.1 Introduction
6.2 Materials and Methods
6.2.1 Data Collection
6.2.2 Methods of Wheat Instance Segmentation
6.2.3 Evaluation Metric
6.3 Results
6.3.1 Comparative Evaluation
6.3.2 Ablation Study
6.4 Discussion
6.4.1 Analysis of Experimental Error
6.4.2 Evaluation of Wheat-Net on Barley Spike Detection
6.5 Conclusion
References
7 UAV Multispectral Remote Sensing for Yellow Rust Mapping: Opportunities and Challenges
7.1 Introduction
7.2 UAV Remote Sensing
7.2.1 Wheat Yellow Rust Experiment
7.2.2 UAV Remote Sensing
7.2.3 Image Pre-processing and Data Labelling
7.3 Yellow Rust Disease Mapping
7.3.1 Spectral Analysis
7.3.2 Mutual Information Ranking
7.3.3 Unsupervised Classification
7.4 Discussion
7.4.1 Pros and Cons
7.4.2 Challenges for Real-Life Applications
7.5 Conclusions
References
8 Corn Goss’s Wilt Disease Assessment Based on UAV Imagery
8.1 Introduction
8.2 Material and Methodology
8.2.1 Data Collection and Data Preprocessing
8.2.2 Preparation of Datasets
8.2.3 Training and Validation of ML and DL Algorithms
8.2.4 Results
8.2.5 Discussion
8.2.6 Conclusion
References
