Hydra-Bench: A Benchmark for Multi-Modal Leaf Wetness Sensing

TL;DR

Hydra-Bench introduces a comprehensive multi-modal dataset and benchmark for leaf wetness detection, combining mmWave, SAR, and RGB data to improve robustness and accuracy in real-world agricultural conditions.

Contribution

The paper presents a new multi-modal dataset and benchmark for leaf wetness detection, enabling systematic evaluation and advancement of machine learning algorithms in this domain.

Findings

Hydra model outperforms single modality baselines.

Fusion strategies improve detection accuracy.

Dataset enables evaluation under diverse environmental conditions.

Abstract

Leaf wetness detection is a crucial task in agricultural monitoring, as it directly impacts the prediction and protection of plant diseases. However, existing sensing systems suffer from limitations in robustness, accuracy, and environmental resilience when applied to natural leaves under dynamic real-world conditions. To address these challenges, we introduce a new multi-modal dataset specifically designed for evaluating and advancing machine learning algorithms in leaf wetness detection. Our dataset comprises synchronized mmWave raw data, Synthetic Aperture Radar (SAR) images, and RGB images collected over six months from five diverse plant species in both controlled and outdoor field environments. We provide detailed benchmarks using the Hydra model, including comparisons against single modality baselines and multiple fusion strategies, as well as performance under varying scan distances. Additionally, our dataset can serve as a benchmark for future SAR imaging algorithm optimization, enabling a systematic evaluation of detection accuracy under diverse conditions.