An Edge Computing-Based Solution for Real-Time Leaf Disease Classification Using Thermal Imaging

P. Silva

doi:10.1109/LGRS.2024.3456637

An Edge Computing-Based Solution for Real-Time Leaf Disease Classification Using Thermal Imaging

2025-01-01

0

OA

AI

DOI：10.1109/LGRS.2024.3456637

Original

Original request for help

Save

Abstract

En 中文

Deep learning (DL) technologies can transform agriculture by improving crop health monitoring and management, thus improving food safety. In this letter, we explore the potential of edge computing (EC) for real-time classification of leaf diseases using thermal imaging. We present a thermal image dataset for plant disease classification and evaluate DL models, including InceptionV3, MobileNetV1, MobileNetV2, and VGG-16, on resource-constrained devices like the Raspberry Pi 4B. Using pruning and quantization-aware training, these models achieve inference times up to 1.48x faster on Edge TPU Max for VGG16, and up to 2.13x faster with precision reduction on Intel NCS2 for MobileNetV1, compared with high-end GPUs like RTX 3090, while maintaining state-of-the-art accuracy.

Keywords:

Infrared imaging

neural network compression

real-time systems

remote sensing

Infrared imaging

neural network compression

real-time systems

remote sensing

An Edge Computing-Based Solution for Real-Time Leaf Disease Classification Using Thermal Imaging

Abstract

Journal

Organization