Hydra-Bench: A Benchmark for Multi-Modal Leaf Wetness Sensing
This provides a benchmark for advancing machine learning in agricultural sensing, though it is incremental as it focuses on dataset creation and evaluation rather than a novel method.
The paper tackles the problem of leaf wetness detection for agricultural monitoring by introducing a new multi-modal dataset with synchronized mmWave, SAR, and RGB images, and benchmarks show improved accuracy and robustness under diverse conditions.
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.