MARIDA: Marine Debris Archive

MARIne Debris Archive (MARIDA) is a marine debris-oriented dataset on Sentinel-2 satellite images. It also includes various sea features that co-exist. MARIDA is primarily focused on the weakly supervised pixel-level semantic segmentation task. <strong>Citation: </strong>Kikaki K, Kakogeorgiou I, Mikeli P, Raitsos DE, Karantzalos K (2022) MARIDA: A benchmark for Marine Debris detection from Sentinel-2 remote sensing data. PLoS ONE 17(1): e0262247. https://doi.org/10.1371/journal.pone.0262247 For the quick start guide visit marine-debris.github.io The dataset contains: i. 1381 patches (256 x 256) structured by Unique Dates and S2 Tiles. Each patch is provided along with the corresponding masks of pixel-level annotated classes (*_cl) and confidence levels (*_conf). Patches are given in GeoTiff format. ii. Shapefiles data in WGS’84/ UTM projection, with file naming convention following the scheme: s2_dd-mm-yy_ttt, where s2 denotes the S2 sensor, dd denotes the day, mm the month, yy the year and ttt denotes the S2 tile. Shapefiles include the class of each annotation along with the confidence level and the marine debris report description. iii. Train, Validation and Test split for evaluating machine learning algorithms. iv. The assigned multi-labels for each patch (labels_mapping.txt). The mapping between Digital Numbers and Classes is: 1: Marine Debris<br> 2: Dense Sargassum<br> 3: Sparse Sargassum<br> 4: Natural Organic Material<br> 5: Ship<br> 6: Clouds<br> 7: Marine Water<br> 8: Sediment-Laden Water<br> 9: Foam<br> 10: Turbid Water<br> 11: Shallow Water<br> 12: Waves<br> 13: Cloud Shadows<br> 14: Wakes<br> 15: Mixed Water The mapping between Digital Numbers and Confidence level is: 1: High<br> 2: Moderate<br> 3: Low The mapping between Digital Numbers and marine debris Report existence is: 1: Very close<br> 2: Away<br> 3: No The final uncompressed dataset requires 4.38 GB of storage.海洋垃圾档案数据集（Marine Debris Archive, MARIDA）是一款面向海洋垃圾的哨兵2号（Sentinel-2）卫星影像数据集，同时涵盖多种共存的海洋地表特征。该数据集主要聚焦于弱监督像素级语义分割任务。<strong>引用文献：</strong>Kikaki K, Kakogeorgiou I, Mikeli P, Raitsos DE, Karantzalos K (2022) MARIDA: 基于哨兵2号遥感数据的海洋垃圾检测基准数据集。PLoS ONE 17(1): e0262247. https://doi.org/10.1371/journal.pone.0262247。如需获取快速入门指南，请访问 marine-debris.github.io。该数据集包含以下内容： i. 1381幅尺寸为256×256的影像块，按唯一成像日期与S2瓦片进行组织。每幅影像块均附带对应像素级标注类别的掩膜文件（*_cl）与置信度层级文件（*_conf），影像块采用GeoTiff格式存储。 ii. 采用WGS84/UTM投影的Shapefile（形状文件）数据，文件名遵循如下命名规则：`s2_dd-mm-yy_ttt`，其中`s2`代表S2传感器，`dd`为日期，`mm`为月份，`yy`为年份，`ttt`为S2瓦片编号。该形状文件包含各标注的类别信息、置信度等级以及海洋垃圾报告描述内容。 iii. 用于机器学习算法评估的训练集、验证集与测试集划分方案。 iv. 每幅影像块的分配多标签信息（labels_mapping.txt）。 数字值与类别的映射关系如下： 1: 海洋垃圾 2: 密集马尾藻 3: 稀疏马尾藻 4: 天然有机物质 5: 船舶 6: 云 7: 海水 8: 含泥沙水体 9: 泡沫 10: 浑浊水体 11: 浅水区 12: 海浪 13: 云影 14: 尾迹 15: 混合水体 数字值与置信度等级的映射关系如下： 1: 高 2: 中等 3: 低 数字值与海洋垃圾报告存在性的映射关系如下： 1: 极近距离 2: 远距离 3: 无 最终未压缩的数据集总存储空间需求为4.38 GB。