Coal site related datasets

The constructed dataset comprises two representative scene types. The open-pit coal mining scenes (OCMS) include 201 original samples, which yielded 3247 standardized 224×224-pixel samples after target purification. The dataset is split 8:1:1 into training (2597 samples), validation (349 samples), and testing (301 samples). The composite coal-related scenes (CCS) include 272 original samples, which yielded 1531 standardized samples, also divided 8:1:1 into training (1223), validation (154), and testing (154). The difference in sample size reflects the varying complexity of the two scene types: OCMS scenes contain more extractable target regions, whereas CCS scenes are relatively scattered in spatial distribution. This dataset construction approach accounts for the unique characteristics of each scene, ensuring an adequately balanced and representative sample foundation for subsequent model training.

本数据集共包含两类典型场景。露天煤矿开采场景（Open-pit Coal Mining Scenes，OCMS）初始包含201份原始样本，经目标提纯处理后，得到3247份规格为224×224像素的标准化样本；数据集按8:1:1的比例划分为训练集（2597份）、验证集（349份）与测试集（301份）。复合煤炭相关场景（Composite Coal-related Scenes，CCS）初始包含272份原始样本，经标准化处理后得到1531份标准化样本，同样以8:1:1的比例划分为训练集（1223份）、验证集（154份）与测试集（154份）。两类场景的样本量差异反映了其复杂程度的不同：露天煤矿开采场景可提取的目标区域更多，而复合煤炭相关场景的空间分布相对分散。本数据集的构建方式充分兼顾了两类场景的独有特性，为后续模型训练提供了均衡且具有充分代表性的样本基础。

搜集汇总

背景与挑战

背景概述

该数据集包含两种煤矿场景图像（OCMS和CCS），分别有3247和1531个标准化样本，按8:1:1比例划分为训练、验证和测试集，适用于AI和遥感研究。