Learning Adversarial Augmentation Policies for Robust Garlic Seedling Detection

2026-06-25

AI Summary

This study addresses the limited robustness of garlic seedling detection under complex outdoor lighting conditions by constructing a real-world dataset and proposing an adversarial augmentation strategy learning framework. During training, the framework jointly optimizes a stochastic augmentation policy agent and an object detector. A structural penalty mechanism is introduced to prevent the generation of unrealistic deformations while encouraging challenging yet plausible augmented samples, thereby enhancing the model’s robust feature representation under extreme illumination without incurring additional inference overhead. Experimental results demonstrate that the proposed method achieves an AP$_{50}$ of 91.6% (+0.9%), with missing seedling localization accuracy and F1-score reaching 75.0% (+4.8%) and 67.0% (+2.0%), respectively.

Abstract

Accurate seedling detection during early growth stages is essential for timely replanting and effective crop management in precision agriculture. However, existing studies are mostly evaluated under relatively stable imaging conditions, such as UAV imagery or greenhouse environments, leaving robust detection under severe and spatially heterogeneous illumination in ground-based outdoor monitoring insufficiently explored. In addition, many illumination-robust detection methods rely on additional enhancement or feature-extraction modules, which increase inference-time overhead and are not tailored to seedling detection and downstream missing seedling localization. To address these gaps, we construct a new garlic seedling dataset captured using a ground-based monitoring platform under real outdoor field conditions with highly variable illumination. We further propose an illumination-robust seedling detection framework based on adversarial augmentation policy learning. The proposed method jointly optimizes a stochastic augmentation policy agent and an object detector, enabling the detector to learn robust representations under challenging visual conditions. A structural penalty is introduced to prevent unrealistic distortions while encouraging challenging augmentations during training. Extensive experiments show that the proposed approach achieves an AP$_{50}$ of 91.6%, improving the baseline by 0.9 percentage points and outperforming the previous best-performing method by 0.2 percentage points. For downstream missing seedling localization, it achieves 75.0% precision and a 67.0% F1-score, improving the baseline by 4.8 and 2.0 percentage points, respectively. These results demonstrate the effectiveness of the proposed framework for practical ground-based agricultural monitoring under complex outdoor lighting conditions without additional inference-time computational overhead.

Problem

• garlic seedling detection
• illumination robustness
• ground-based monitoring
• adversarial augmentation
• outdoor field conditions

Innovation

• adversarial augmentation
• illumination-robust detection
• seedling detection
• policy learning
• ground-based monitoring