Technology Category
Computer Vision: Object Detection & CategorizationMachine Learning: Hardware-aware MLIntelligent Robots: Multimodal Perception & Sensor Fusion
A Low-Cost UAV Deep Learning Pipeline for Integrated Apple Disease Diagnosis,Freshness Assessment, and Fruit Detection
🤖 AI Summary
Current smart orchard monitoring systems predominantly rely on expensive multispectral UAVs, with disease detection, fruit quality assessment, and yield estimation treated as isolated tasks—resulting in high costs and deployment complexity. This paper proposes the first end-to-end embedded analysis system based on low-cost RGB UAVs, unifying leaf disease classification, fruit freshness evaluation, and fruit detection/localization on a single platform. The system is fully deployed offline on resource-constrained edge devices—ESP32-CAM and Raspberry Pi—integrating lightweight variants of ResNet50 (for disease classification), VGG16 (for freshness assessment), and YOLOv8 (for fruit detection), eliminating cloud dependency. Experimental results demonstrate classification accuracy of 98.9% for leaf diseases, 97.4% for fruit freshness recognition, and an F1-score of 0.857 for fruit detection. These findings validate the feasibility of RGB-based sensing for high-accuracy, practical agricultural AI, significantly reducing hardware cost and lowering the barrier to adoption.
Technology Category
Application Category
📝 Abstract
Apple orchards require timely disease detection, fruit quality assessment, and yield estimation, yet existing UAV-based systems address such tasks in isolation and often rely on costly multispectral sensors. This paper presents a unified, low-cost RGB-only UAV-based orchard intelligent pipeline integrating ResNet50 for leaf disease detection, VGG 16 for apple freshness determination, and YOLOv8 for real-time apple detection and localization. The system runs on an ESP32-CAM and Raspberry Pi, providing fully offline on-site inference without cloud support. Experiments demonstrate 98.9% accuracy for leaf disease classification, 97.4% accuracy for freshness classification, and 0.857 F1 score for apple detection. The framework provides an accessible and scalable alternative to multispectral UAV solutions, supporting practical precision agriculture on affordable hardware.
Problem
Research questions and friction points this paper is trying to address.
Integrates apple disease detection, freshness assessment, and fruit localization using a single low-cost UAV system
Eliminates reliance on expensive multispectral sensors by employing only RGB cameras
Enables fully offline on-site inference for practical precision agriculture applications
Innovation
Methods, ideas, or system contributions that make the work stand out.
Uses RGB-only UAV with ResNet50, VGG16, YOLOv8
Runs offline on ESP32-CAM and Raspberry Pi
Integrates disease, freshness, detection in one pipeline
🔎 Similar Papers
No similar papers found.
