ISIISNet : plankton images captured with the ISIIS (In-situ Ichthyoplankton Imaging System)

plankton was imaged with an in situ ichthyoplankton imaging system, between surface and ~100m, over 10 days in july 2016, in the north western mediterranean sea. this deployment was the core of the visufront cruise. the image generated by the linescan, shadowgraph camera of isiis were processed with the custom software apeep and regions of interest, targeted to be planktonic organisms by a deep segmenter, were extracted. the 408,166 resulting objects were sorted by a limited number of operators, following a common taxonomic guide, into 32 taxa, using the web application ecotaxa http://ecotaxa.obs-vlfr.fr. for the purpose of training machine learning classifiers, the images in each class were split into training, validation, and test sets, with proportions 70%, 15% and 15%.the archive contains :taxa.csv.gztable of the classification of each object in the dataset, with columns : objid: id of the object (in ecotaxa) taxon_level1: name of the taxon corresponding to the level 1 classification lineage_level1: taxonomic lineage corresponding to the level 1 classification taxon_level2: name of the taxon corresponding to the level 2 classification plankton: indicates if the object is a plankton (boolean) set: class of the image corresponding to the taxon (train : training, val : validation, or test) img_path: local path of the image corresponding to the taxon (of level 1), named according to the object idfeatures_native.csv.gztable of morphological features recomputed with skimage.measure.regionprops on the rois produced by software. see http://scikit-image.org/docs/dev/api/skimage.measure.html#skimage.measure.regionprops for documentation.inventory.tsvtree view of the taxonomy and number of images in each taxon, displayed as text. with columns : lineage_level1: taxonomic lineage corresponding to the level 1 classification taxon_level1: name of the taxon corresponding to the level 1 classification n: number of objects in each taxon class map.pngmap of the sampling locations, to give an idea of the diversity sampled in this dataset.imgsdirectory containing images of each object, named according to the object id objid and sorted in subdirectories according to their taxon.

该数据集采用原位浮游动物成像系统对浮游生物进行了拍摄，成像范围介于水面至约100米之间，拍摄时间跨越2016年7月的10天，地点位于地中海西北部。此次部署构成了Visufront航次的主体。ISIIS的线条扫描、阴影图相机生成的图像经过定制软件APEEP处理，并通过深度分割器提取了目标为浮游生物的感兴趣区域。经过有限数量操作员的分类，基于通用的分类指南，将408,166个结果对象归入32个分类，利用Web应用程序Ecotaxa（http://ecotaxa.obs-vlfr.fr）进行。为训练机器学习分类器，每个分类中的图像被划分为训练集、验证集和测试集，比例为70%、15%和15%。该档案包含以下内容：
taxa.csv.gz：包含数据集中每个对象的分类表格，列包括：
objid：对象的ID（在Ecotaxa中）；
taxon_level1：对应一级分类的物种名称；
lineage_level1：对应一级分类的分类系统；
taxon_level2：对应二级分类的物种名称；
plankton：指示对象是否为浮游生物（布尔值）；
set：对应物种的一级分类的图像类别（train：训练，val：验证，或test：测试）；
img_path：对应物种的一级分类的图像的本地路径，按对象ID命名。
features_native.csv.gz：包含使用skimage.measure.regionprops对由软件产生的感兴趣区域重新计算的形态学特征表格。有关文档，请参阅http://scikit-image.org/docs/dev/api/skimage.measure.html#skimage.measure.regionprops。
inventory.tsv：展示分类系统和每个分类中图像数量的树状视图，列包括：
lineage_level1：对应一级分类的分类系统；
taxon_level1：对应一级分类的物种名称；
n：每个分类中对象的数量。
class map.png：采样位置的地图，以展示本数据集中所采集的多样性。
images目录：包含每个对象的图像，按对象ID命名，并根据物种分类在子目录中进行排序。