Computer Vision and Machine Learning in Agriculture

✍ Scribed by Mohammad Shorif Uddin (editor), Jagdish Chand Bansal (editor)

• Publisher: Springer
• Year: 2022
• Tongue: English
• Leaves: 269
• Series: Algorithms for Intelligent Systems
• Category: Library

✦ Synopsis

This book is as an extension of previous book “Computer Vision and Machine Learning in Agriculture” for academicians, researchers, and professionals interested in solving the problems of agricultural plants and products for boosting production by rendering the advanced machine learning including deep learning tools and techniques to computer vision algorithms. The book contains 15 chapters. The first three chapters are devoted to crops harvesting, weed, and multi-class crops detection with the help of robots and UAVs through machine learning and deep learning algorithms for smart agriculture. Next, two chapters describe agricultural data retrievals and data collections. Chapters 6, 7, 8 and 9 focuses on yield estimation, crop maturity detection, agri-food product quality assessment, and medicinal plant recognition, respectively. The remaining six chapters concentrates on optimized disease recognition through computer vision-based machine and deep learning strategies.

✦ Table of Contents

Preface
Contents
Editors and Contributors
1 Harvesting Robots for Smart Agriculture
1 Introduction
2 Related Literature
3 Basics of Harvesting Robots
4 Robots in Harvesting Applications
4.1 Harvesting Robots in Path Navigation
4.2 Crops and Vegetable Harvesting
5 Commercialization and Current Challenges of Harvesting Robots
6 Conclusion
References
2 Drone-Based Weed Detection Architectures Using Deep Learning Algorithms and Real-Time Analytics
1 Introduction
2 Overview of UAVs, Artificial Intelligence and Spark Architecture
2.1 Evolution of UAVs
2.2 Applications of UAVs
2.3 UAVs in Agriculture
2.4 UAVs in Weed Detection and Management
2.5 Evolution of Distributed and Parallel Computing for Real-Time Performance
2.6 Spark Architecture
2.7 Spark Streaming Architecture
2.8 Artificial Neural Networks and Deep Learning
3 Proposed Architectures
3.1 Model 1—Conventional Server-Based Architecture
3.2 Model 2—Single-Tier UAV-Based Architecture
3.3 Model 3—Double-Tier UAV-Based Architecture
3.4 Model 4—Hybrid UAV Architecture
4 Conclusion
References
3 A Deep Learning-Based Detection System of Multi-class Crops and Orchards Using a UAV
1 Introduction
2 Related Work
3 Materials and Methods
3.1 Data Collection
3.2 Data Preprocessing and Data Enhancement
3.3 Optimized Faster-RCNN
3.4 Proposed Real-Time Framework Description
4 Results and Discussion
5 Conclusion
References
4 Real-Life Agricultural Data Retrieval for Large-Scale Annotation Flow Optimization
1 Introduction
2 Previous Work
3 Optimized Annotation Flow
4 Crop Identification
4.1 Data Preparation
4.2 Model and Hyperparameters
4.3 Results
5 Emergence Analysis
5.1 Data Preparation
5.2 Model Versions and Hyperparameters
5.3 Results
5.4 Feature Vectors Clustering
6 Conclusion
References
5 Design and Analysis of IoT-Based Modern Agriculture Monitoring System for Real-Time Data Collection
1 Introduction
2 Proposed System Model
2.1 IoT Sensor Nodes
2.2 Controllers and Processing Units
2.3 Communication Technologies
2.4 Cloud Storage and Local Database
2.5 Energy Solution
3 Experimental Setup
4 Simulation Results and Discussion
5 Conclusion
References
6 Estimation of Wheat Yield Based on Precipitation and Evapotranspiration Using Soft Computing Methods
1 Introduction
2 Materials and Methods
2.1 Crop Water Requirement
2.2 Description of the Methods
3 Results
4 Conclusions
References
7 Coconut Maturity Recognition Using Convolutional Neural Network
1 Introduction and Related Works
2 Development of Coconut Image Database
2.1 Image Acquisition and Preprocessing
2.2 Image Categorization
2.3 Ground Truth Image Creation
2.4 Image Augmentation
3 Materials and Methods
3.1 Convolutional Neural Networks
4 Experimental Results
5 Performance Evaluation Analyses
5.1 Coconut Maturity Stages Recognition
6 Conclusion
References
8 Agri-Food Products Quality Assessment Methods
1 Introduction
2 Techniques for Food Quality Analysis
3 Imaging Techniques for Quality Assessment
4 Spectroscopic Methods for Food Quality Analysis
5 Role of Machine Learning and Deep Learning in Food Quality Evaluation
6 Blockchain-Based Grading Mechanism
7 Conclusion
References
9 Medicinal Plant Recognition from Leaf Images Using Deep Learning
1 Introduction
2 Literature Review
3 Research Methodology
4 Data Collection and Preprocessing
5 Experimental Evaluation
6 Comparative Analysis of Results
7 Conclusion and Future Work
References
10 ESMO-based Plant Leaf Disease Identification: A Machine Learning Approach
1 Introduction
2 Methodology
2.1 Spider Monkey Optimization
2.2 Proposed ESMO: a Plant Disease Identification Approach
2.3 Exponential SMO
2.4 Feature Extraction
2.5 Feature Selection
2.6 Performance Comparison
2.7 Classifier
3 Results
4 Conclusions and Future Work
References
11 Deep Learning-Based Cauliflower Disease Classification
1 Introduction
2 Related Works
3 Materials and Methods
3.1 Dataset
3.2 Convolutional Neural Network (CNN)
3.3 State-of-the-Art CNN Architectures
3.4 Computational Environment
3.5 Training
4 Result Analysis
5 Conclusion
References
12 An Intelligent System for Crop Disease Identification and Dispersion Forecasting in Sri Lanka
1 Introduction
2 Background Study
3 Research Methodology
3.1 Solution Design
3.2 Selection of Neural Network Models
3.3 Data Gathering for the Image Pools
3.4 Implement the Neural and Transfer Learning Models
3.5 Identification of Disease Progression
3.6 Visualization of Disease Propagation
4 Results and Discussion
5 Conclusion
References
13 Apple Leaves Diseases Detection Using Deep Convolutional Neural Networks and Transfer Learning
1 Introduction
2 Literature Review
3 Proposed Methodology
3.1 Dataset
3.2 Data Preprocessing
3.3 Data Augmentation
3.4 Models and Methods
4 Experimental Results
4.1 Experimental Setup
4.2 Evaluation Metrics
4.3 Performance Evaluation
5 Conclusion
References
14 A Deep Learning Paradigm for Detection and Segmentation of Plant Leaves Diseases
1 Introduction
2 Related Work
3 Methodology
3.1 Proposed Object Detection Architecture-1
3.2 Proposed Instance Segmentation Architecture 2
4 Image Dataset Acquisition
5 Experimental Setup and Results Analysis
5.1 Performance Measures
5.2 Experimental Setup and Results Discussions
6 Conclusion and Future Work
References
15 Early Stage Prediction of Plant Leaf Diseases Using Deep Learning Models
1 Introduction
2 Literature Survey
3 Types of Plants Diseases
4 Preliminary Overview
4.1 Convolutional Neural Network
4.2 Support Vector Machines
4.3 Extreme Gradient Boosting (XGBoost)
4.4 Proposed Method
4.5 Multiple Feature Extraction
5 Result and Discussion
5.1 Dataset
5.2 Performance Evaluation
6 Conclusion
References