原文链接：
https://link.springer.com/article/10.1007/s40789-023-00622-4或点击文末“阅读原文”
矿山排土场的结构完整性对于采矿作业至关重要，以避免对经济、社会和环境的负面影响。为确保随着时间推移弃土卸载持续进行并实现设计协调一致，矿山排土场需要进行例行临时评估。传统的原位煤矸石表征方法效率低、费力、危险，且容易出现观察偏差。为此，本研究探索了一种利用基于光学遥感的无人机（UAV）来开发自动煤弃土表征的新方法。在所提出的工作流程中，利用高分辨率无人机图像的纹理和光谱特性来导出岩性和岩土参数（即织物结构和相对密度/稠度）。使用运动辅助处理的结构将原始图像转换为正射马赛克图像。然后，计算每个像素的结构描述符，以增强弃土材料的特征模态。最后，采用机器学习算法和专家提供的真实数据作为训练和测试数据，以最少的人为干预快速表征损坏情况。提出的方法所达到的表征精度体现了一种数字解决方案，可解决传统表征方法的局限性。
Abstract The structural integrity of mine dumps is crucial for mining operations to avoid adverse impacts on the triple bottom-line. Routine temporal assessments of coal mine dumps are a compliant requirement to ensure design reconciliation as spoil offloading continues over time. Generally, the conventional in-situ coal spoil characterisation is inefficient, laborious, hazardous, and prone to experts' observation biases. To this end, this study explores a novel approach to develop automated coal spoil characterisation using unmanned aerial vehicle (UAV) based optical remote sensing. The textural and spectral properties of the high-resolution UAV images were utilised to derive lithology and geotechnical parameters (i.e., fabric structure and relative density/consistency) in the proposed workflow. The raw images were converted to an orthomosaic using structure from motion aided processing. Then, structural descriptors were computed per pixel to enhance feature modalities of the spoil materials. Finally, machine learning algorithms were employed with ground truth from experts as training and testing data to characterise spoil rapidly with minimal human intervention. The characterisation accuracies achieved from the proposed approach manifest a digital solution to address the limitations in the conventional characterisation approach.
Fig. 1 a Location of a selected mine dump site in New South Wales b Selected study area, ground control points (GCPs) and distribution of ground truth sample points in the selected dump site. The size of GCPs and sampling point locations are shown using visual markers, as the original points are not visible in the given map scale. These markers do not correspond to the actual size of the objects on the ground
Fig. 6 Lithological classification produced by a composite of optical data and data transformed with principal component analysis (RGB + PCA) using k-nearest neighbourhood (kNN)
Fig. 9 Overall accuracy and kappa coefficient of classification algorithms on composites formed using optical data and, optical + textural data. Precision, recall and F-score of classifications respectively for a Optical data b Optical + textural data transformed with principal component analysis (RGB + PCA) and c and d Optical + textural data transformed with independent component analysis (RGB + ICA)
引用格式：Thiruchittampalam, S., Singh, S.K., Banerjee, B.P. et al. Spoil characterisation using UAV-based optical remote sensing in coal mine dumps. Int J Coal Sci Technol 10, 65 (2023). https://doi.org/10.1007/s40789-023-00622-4
