Related Experiment Video
Updated: Jun 10, 2025
05:03
Author Spotlight: Advancing Stomatal Research with Automated Aperture Measurement
Published on: February 9, 2024
1.5K
Intelligent agricultural robotic detection system for greenhouse tomato leaf diseases using soft computing techniques
Thi Thoa Mac1, Tien-Duc Nguyen2, Hong-Ky Dang1
1School of Mechanical Engineering, Hanoi University of Science and Technology, 1st Dai Co Viet Road, Hai Ba Trung District, Hanoi, 100000, Vietnam.
Scientific Reports
|October 12, 2024
Summary
This study introduces an upgraded Deep Convolutional Generative Adversarial Network (DCGAN) to improve tomato plant disease detection in autonomous greenhouses. The enhanced dataset significantly boosts deep learning model accuracy for intelligent agriculture.
Area of Science:
- Agricultural Science
- Computer Science
- Artificial Intelligence
Background:
- Soft computing methods are crucial for advancing autonomous intelligent agriculture.
- Accurate disease identification in crops like tomatoes is vital for greenhouse management.
- Existing deep learning models require large, diverse datasets for optimal performance.
Purpose of the Study:
- To develop an autonomous greenhouse navigation system using fuzzy control and deep learning for tomato plant disease classification.
- To introduce an upgraded Deep Convolutional Generative Adversarial Network (DCGAN) for augmenting tomato leaf disease image datasets.
- To compare the performance of various deep learning models for accurate disease identification.
Main Methods:
- Implemented a fuzzy control algorithm for autonomous greenhouse navigation.
- Utilized an upgraded DCGAN to generate augmented images of diseased tomato leaves, enhancing the training dataset.
- Compared four deep learning networks (VGG19, Inception-v3, DenseNet-201, ResNet-152) on the PlantVillage dataset for disease classification.
- Evaluated model performance using validation accuracy on original and augmented datasets.
Main Results:
- ResNet-152 achieved the highest accuracy (97.07%) on the original PlantVillage dataset among the compared models.
- The DCGAN-augmented dataset, when used with ResNet-152, resulted in a significantly improved accuracy of 99.69%.
- The proposed DCGAN effectively enhanced the deep learning model's performance for greenhouse plant monitoring and disease detection.
Conclusions:
- The upgraded DCGAN significantly improves the accuracy of deep learning models for tomato plant disease detection.
- The developed system offers a robust solution for autonomous intelligent agriculture, enhancing greenhouse management.
- The approach shows potential for broad application in various agricultural scenarios, advancing autonomous farming practices.
Related Concept Videos
02:16Light Acquisition
8.4K
In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.
8.4K
02:35Key Elements for Plant Nutrition
18.7K
Like all living organisms, plants require organic and inorganic nutrients to survive, reproduce, grow and maintain homeostasis. To identify nutrients that are essential for plant functioning, researchers have leveraged a technique called hydroponics. In hydroponic culture systems, plants are grown—without soil—in water-based solutions containing nutrients. At least 17 nutrients have been identified as essential elements required by plants. Plants acquire these elements from the...
18.7K