SULAND v2：面向域偏移下基于无人机/无人地面车辆地表地雷探测的精炼RGB数据集与深度学习目标检测基准

摘要

RGB图像为地表地雷探测中的无人机/无人地面车辆（UAV/UGV）勘测支持提供了一种实用且低成本的方案，但目标检测器在这一安全关键领域仍未得到充分探索。有限的跨架构基准测试和不足的分布外（OOD）分析，使检测器能否在不同部署条件下泛化这一问题难以得到明确回答。公共RGB地雷数据集的稀缺进一步加剧了这一挑战，使SULAND成为PFM-1和PMA-2检测的关键基准。然而，检查发现SULAND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约定反转等问题。我们提出SULAND_v2，一个经精炼的RGB地表地雷数据集与基准。在保留原始图像和划分的基础上，我们人工修订标注，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33,771张图像和12,433个边界框。我们评估了九个系列的35种检测器配置。标注精炼使YOLOv8在同分布（IID）测试中的mAP@50提高了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提高了约25个百分点。在SULAND_v2上，YOLOv12-Small取得了最高的IID mAP@50（0.908），而RF-DETR-Large表现出最强的OOD性能（mAP@50为0.799，召回率为0.675）。我们的结果表明，高IID精度并不能保证部署就绪性。SULAND_v2为评估基于RGB的排雷行动勘测支持中的域偏移鲁棒性提供了可靠基准。

English

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.