SCLabels: Labelled rectified RGB images from the Spanish CoastSnap network

Training dataset The SCLabels dataset is intended to be used in the exploring and development of Artificial Intelligence (AI) applications aimed at the automation of the shoreline extraction process from rectified images. SCLabels includes rectified RGB images from the Spanish CoastSnap network and their corresponding masks, together with a metadata file and a README file. RGB images encompass variable geographic locations, fields of view, beach types and degrees of occupation, tidal regimes, meteoceanic and lightning conditions, and a variety of environmental characteristics. Masks account for dense pixel labels including 5 categories: i) No data; ii) Not classified; iii) Landwards; iv) Seawards; and v) Shoreline. In the metadata file, images are linked to their corresponding masks, and information about the geographic location of each image, capture characteristics and image source, shoreline position and other auxiliary data are provided. The README file enhances the explainability and comprehension of the dataset, elaborating on the context and contents, and providing detailed explanations of the metadata, potential limitations, technical aspects of the image processing and annotation stages, usage recommendations, and related works. Technical details The SCLabels dataset version 1.0.0 is packaged in a compressed file (SCLabels_v1.0.0.zip). A total of 1717 RGB images are shared in JPG format, corresponding masks in PNG format, a metadata file in JSON format, and the README file in PDF format. Data preprocessing To generate the SCLabels masks, rectified RGB images and their corresponding shorelines were used. RGB images were cropped to the minimum and maximum alongshore pixel coordinates of the shoreline (vertical axis) plus 10 additional pixels above and below to preserve contextual information. A grayscale image was then derived from each cropped RGB image for subsequent pixel labelling. First, a binary mask was derived, marking "NoData'' for black and white padded pixels resulting from the registration and rectification steps. Subsequently, the shoreline was densified, ensuring at least one pixel per row was assigned the "Shoreline" label. Next, "Landwards" and "Seawards" labels were assigned to the right and left of the shoreline. Pixels left unlabelled were categorised as "NotClassified". Finally, masks’ values were reclassified to align with the predefined labels, and the grayscale masks were exported. For additional information, please consult the README file. Data splitting Data splitting requirements may vary depending on the chosen AI approach (e.g., splitting by entire images, image patches, or image rows). Researchers should use a consistent data splitting method and document the approach and splits used in publications. This transparency enables reproducible results and facilitates comparisons between studies. Classes, labels and annotations The SCLabels dataset includes one mask per rectified RGB image, sharing the same width and height. These masks are in greyscale and PNG format, and consist of five different labels: Mask value Label Description 0 NoData High probability of being black or white padded pixels, used to pad non-rectangular images within the image registration and rectification processes 25 NotClassified Not labeled pixels 75 Landwards All pixels that are towards the landside with respect to the shoreline (row-wise), excluding “NoData” ones 150 Seawards All pixels that are towards the seaside with respect to the shoreline (row-wise), excluding “NoData” ones 255 Shoreline Pixels intersected by the mapped shoreline densified to cover one pixel per row, at least Parameters RGB values or any transformation in the colour space can be used as parameters. Data sources In the CoastSnap initiative, citizens capture images (oblique smartphone photos) from fixed CoastSnap stations and share them with the scientific managers. Images are subjected to a quality control process, spatially registered to a designated target image, and rectified (georeferencing). The shoreline is subsequently digitised from each rectified image. Data quality All images included have been supervised by CSs’ scientific managers. However, citizen scientists take images by smartphones (different camera quality) at irregular intervals across various sites with varying weather and illumination conditions. Users of SCLabels dataset must be aware of this variance. Image resolution The resolution of the images depends on the CoastSnap station and the length of the shoreline, ranging from 241x188 pixels to 801x796 pixels. Spatial coverage The SCLabels dataset version 1.0.0 contains data from five Spanish CoastSnap stations, including sandy beaches in the northwest (agrelo), the Cíes Islands (cies), the south (cadiz), and the Balearic Islands (samarador and arenaldentem). CoastSnap station Longitude Latitude agrelo -8.772 42.331 cies -8.900 42.226 cadiz -6.288 36.522 samarador 3.185 39.350 arenaldentem 2.974 39.353 Contact information For further technical inquiries or additional information about the annotated dataset, please contact [e-mail].训练数据集 SCLabels数据集旨在用于探索与开发面向从校正图像（rectified images）中自动化提取海岸线流程的人工智能（Artificial Intelligence, AI）应用。SCLabels数据集包含来自西班牙CoastSnap网络的校正RGB图像及其对应的掩码（mask）文件，同时附带元数据（metadata）文件与README文件。RGB图像涵盖了多样的地理位置、视场范围（field of view）、海滩类型与开发程度、潮汐状况（tidal regimes）、海洋气象（meteoceanic）与光照条件，以及多种环境特征。掩码包含稠密的像素标签，共分为5个类别：i) 无数据（No data）；ii) 未分类（Not classified）；iii) 向陆侧（Landwards）；iv) 向海侧（Seawards）；v) 海岸线（Shoreline）。在元数据文件中，图像与其对应的掩码建立了关联，并提供了每张图像的地理位置、拍摄特征、图像来源、海岸线位置及其他辅助数据信息。README文件旨在提升数据集的可解释性与可理解性，详细阐述了数据集的背景与内容，并对元数据、潜在局限性、图像处理与标注阶段的技术细节、使用建议以及相关研究成果进行了详尽说明。 技术细节 SCLabels数据集1.0.0版本打包为压缩文件（SCLabels_v1.0.0.zip）。其中共包含1717张JPG格式的RGB图像、对应的PNG格式掩码文件、JSON格式元数据文件以及PDF格式的README文件。 数据预处理 为生成SCLabels数据集的掩码，本数据集使用了校正后的RGB图像及其对应的海岸线数据。首先将RGB图像裁剪至海岸线沿岸像素坐标的最小值与最大值（垂直轴）范围，并在上下各额外保留10个像素以保留上下文信息；随后从每张裁剪后的RGB图像中提取灰度图像，用于后续的像素标注。首先生成二值掩码（binary mask），将配准与校正步骤中产生的黑白填充像素标记为“无数据（NoData）”；随后对海岸线进行稠密化处理，确保每一行至少有一个像素被标注为“海岸线（Shoreline）”；接下来，将海岸线左侧与右侧分别标注为“向陆侧（Landwards）”与“向海侧（Seawards）”；未被标注的像素归类为“未分类（NotClassified）”；最后，将掩码的像素值重新分类以匹配预定义的标签，并导出灰度掩码。如需更多信息，请参阅README文件。 数据划分 数据划分的要求会因所选的人工智能方法而异（例如按完整图像、图像块（image patches）或图像行进行划分）。研究人员应采用统一的数据划分方法，并在发表的成果中记录所使用的划分方法与划分结果。这种透明度可确保结果可复现，并便于不同研究之间的对比。 类别、标签与标注 SCLabels数据集为每张校正RGB图像配备一个掩码，二者的宽高保持一致。该掩码采用灰度PNG格式，包含以下五种不同的标签： | 掩码像素值 | 标签 | 描述 | | --- | --- | --- | | 0 | 无数据（NoData） | 为图像配准与校正流程中用于填充非矩形图像的黑白填充像素，出现概率较高 | | 25 | 未分类（NotClassified） | 未被标注的像素 | | 75 | 向陆侧（Landwards） | 相对于海岸线（按行划分）朝向陆地方向的所有像素，不含无数据像素 | | 150 | 向海侧（Seawards） | 相对于海岸线（按行划分）朝向海洋方向的所有像素，不含无数据像素 | | 255 | 海岸线（Shoreline） | 与绘制海岸线相交的像素，经稠密化处理后确保每一行至少覆盖一个该标签像素 | 参数 可将RGB像素值或色彩空间（colour space）中的任意变换结果作为模型参数。 数据来源 在CoastSnap项目中，普通民众通过固定的CoastSnap站点拍摄图像（倾斜智能手机照片）并分享给科学管理人员。所有图像需经过质量控制流程，被空间配准至指定目标图像后进行校正（地理配准（georeferencing））；随后从每张校正后的图像中数字化提取海岸线。 数据质量 本数据集包含的所有图像均经过CoastSnap科学管理人员的审核。但普通民众使用智能手机（相机质量参差不齐）在不同站点以非固定间隔拍摄图像，且拍摄时的天气与光照条件存在差异。SCLabels数据集的使用者需注意此类数据异质性。 图像分辨率 图像分辨率取决于CoastSnap站点与海岸线长度，范围为241×188像素至801×796像素。 空间覆盖范围 SCLabels数据集1.0.0版本包含5个西班牙CoastSnap站点的数据，涉及西北部的阿格雷洛（agrelo）、西斯群岛（cies）、南部的加的斯（cadiz）以及巴利阿里群岛的萨马多拉（samarador）与阿雷纳尔登特姆（arenaldentem）的沙滩。 | CoastSnap站点 | 经度 | 纬度 | | --- | --- | --- | | agrelo | -8.772 | 42.331 | | cies | -8.900 | 42.226 | | cadiz | -6.288 | 36.522 | | samarador | 3.185 | 39.350 | | arenaldentem | 2.974 | 39.353 | 联系方式 如需进一步的技术咨询或获取该标注数据集的更多信息，请联系[e-mail]。