SULAND v2：面向域偏移场景下基于无人机/无人地面车辆（UAV/UGV）的地面地雷检测的优化RGB数据集与深度学习目标检测基准
SULAND v2: A Refined RGB Dataset and Deep Learning Object Detection Benchmark for UAV/UGV-Based SUrface LANDmine Detection Under Domain Shift
浏览论文内容
中文总结 AI 辅助
本文针对原SULAND数据集的缺陷推出优化版SULAND_v2，含33771张图像与12433个边界框，通过修正标注并测试35种检测器配置，发现高IID精度不代表可投入实际使用，为地雷检测提供可靠基准。
中文摘要 AI 辅助
RGB图像为无人机/无人地面车辆（UAV/UGV）开展地面地雷检测调查提供了实用、低成本的选择，但在这一安全关键领域，目标检测器的应用仍未得到充分探索。有限的跨架构基准测试和不足的分布外（OOD）分析，使得检测器能否在部署条件间泛化尚不明确，而公开RGB地雷数据集的稀缺进一步加剧了这一挑战，让SULAND成为PFM-1和PMA-2地雷检测的关键基准。不过，对SULAND的检查发现其存在标注缺失/错误、定位误差、可见性标准不一致、视觉伪影、时间标注不一致以及OOD类别ID约定倒置等问题。本文提出SULAND_v2，这是一个优化后的RGB地面地雷数据集与基准。在保留原始图像和划分的基础上，我们手动修正标注以确保完整性、精确定位、标签有效性和类别一致性。SULAND_v2包含33771张图像和12433个边界框。我们对9个系列的35种检测器配置进行基准测试。标注优化使YOLOv8的分布内（IID）测试mAP@50提升了14.6至19.6个百分点，而修正OOD类别ID约定使YOLOv8的平均OOD mAP@50提升约25个百分点。在SULAND_v2上，YOLOv12-Small实现了最高的IID mAP@50（0.908），而RF-DETR-Large则取得了最强的OOD性能（mAP@50为0.799，召回率为0.675）。我们的结果表明，高IID精度并不保证可投入实际使用。SULAND_v2为评估基于RGB的排雷调查支持中的域偏移鲁棒性提供了可靠基准。
英文摘要
RGB imagery offers a practical, low-cost option for Unmanned Aerial/Ground Vehicle (UAV/UGV) survey support in surface-landmine detection, but object detectors remain underexplored in this safety-critical domain. Limited cross-architecture benchmarking and insufficient out-of-distribution (OOD) analysis obscure whether detectors generalize across deployment conditions. This challenge is amplified by the scarcity of public RGB landmine datasets, making SULAND a key benchmark for PFM-1 and PMA-2 detection. However, inspection reveals missing/false annotations, localization errors, inconsistent visibility criteria, visual artifacts, temporal labeling inconsistencies, and an inverted OOD class-ID convention in SULAND. We present SULAND_v2, a refined RGB surface-landmine dataset and benchmark. Preserving original images and splits, we manually revise annotations to ensure completeness, precise localization, label validity, and class consistency. SULAND_v2 contains 33,771 images and 12,433 bounding boxes. We benchmark 35 detector configurations across nine families. Annotation refinement improves YOLOv8 in-distribution (IID) test mAP@50 by 14.6-19.6 percentage points, while fixing the OOD class-ID convention increases mean YOLOv8 OOD mAP@50 by ~25 percentage points. On SULAND_v2, YOLOv12-Small achieves the highest IID mAP@50 (0.908), while RF-DETR-Large yields the strongest OOD performance (0.799 mAP@50, 0.675 recall). Our results demonstrate that high IID accuracy does not guarantee operational readiness. SULAND_v2 provides a reliable benchmark for evaluating domain-shift robustness in RGB-based mine-action survey support.
发表机构
- Rochester Institute of Technology（罗切斯特理工学院）
- Institute of Engineering, Tribhuvan University（特里布万大学工程学院）
机构由 AI 辅助整理，请以论文原文为准。
