Tiny-PMDet: A Knowledge-Distilled Lightweight Edge-AI Detector for Grapevine Powdery Mildew Detection on CMOS Sensor Based AIoT Systems
- 13 March 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on AgriFood Electronics
- Vol. 4 (1) , 383-394
Abstract
Edge-AI-powered Artificial Intelligence of Things (AIoT) technologies enable low-power and efficient solutions for intelligent crop monitoring. This article presents Tiny-PMDet, a lightweight yet high-accuracy detector designed for on-sensor grapevine powdery mildew detection using an edge-AI-enabled CMOS (Sony IMX500) based camera. The proposed model integrates an EfficientNet-Lite0 backbone, a sBiFPN neck, and a lightweight decoupled detection head, achieving an effective balance between detection accuracy and computational efficiency. To further enhance detection precision without increasing inference cost, a loss optimization strategy combining Weighted Cross-Entropy, Efficient IoU, and Quality Cross-Entropy is adopted, together with a dual knowledge distillation scheme based on Pearson correlation and cross-head guidance. Experimental results demonstrate that Tiny-PMDet achieves 95.1% AP@0.5 and 94.4% F1-score, outperforming state-of-the-art lightweight detectors while maintaining a lightweight model size of 2.9 MB and a low computational cost of 0.9 GFLOPs. After posttraining quantization and deployment on the IMX500 sensor, Tiny-PMDet achieves real-time inference at 36 FPS with only an approximately 1% accuracy degradation. These results highlight the advantages of edge-AI CMOS sensor-based solutions for enabling low-power, on-site, and network-independent agricultural monitoring, marking a significant step toward scalable AIoT-driven smart agriculture.Keywords
Funding Information
- SONY Corporation
This publication has 35 references indexed in Scilit:
- Edge AI-enabled chicken health detection based on enhanced FCOS-Lite and knowledge distillationComputers and Electronics in Agriculture, 2024
- MCDCNet: Multi-scale constrained deformable convolution network for apple leaf disease detectionComputers and Electronics in Agriculture, 2024
- FormerLeaf: An efficient vision transformer for Cassava Leaf Disease detectionComputers and Electronics in Agriculture, 2022
- Detection of powdery mildew on strawberry leaves based on DAC-YOLOv4 modelComputers and Electronics in Agriculture, 2022
- An effective litchi detection method based on edge devices in a complex sceneBiosystems Engineering, 2022
- End-to-End Object Detection with Transformers2020
- Grape disease image classification based on lightweight convolution neural networks and channelwise attentionComputers and Electronics in Agriculture, 2020
- A comparative study of fine-tuning deep learning models for plant disease identificationComputers and Electronics in Agriculture, 2019
- IoT and agriculture data analysis for smart farmComputers and Electronics in Agriculture, 2019
- ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design2018