Sentinel-1 SAR Oil spill image dataset for train, validate, and test deep learning models. Part I.
收藏资源简介：
This image dataset: "Sentinel-1 SAR Oil spill image dataset for train, validate, and test deep learning models. Part I", is the first part of the image dataset for train and validate deep learning models for oil spill detection and segmentation. This part contains only the training and validation images for Oil spill. The dataset comprises Sentinel-1 SAR images in Sigma0, in decibels (db), along with their ground truth. The images are 2048x2048x2, also the ground truth is 2048x2048; all of them are in TIFF format. The files are organized in the following manner: 01_Train_Val_Oil_Spill_images consist of 1200 Sentinel-1 SAR Sigma0 images, in db, that correspond to oil spills. 01_Train_Val_Oil_Spill_mask: There are 1200 images in the database corresponding to the ground truth of Sentinel-1 SAR Sigma0 images of oil spills. The foreground is assigned a value of 1, while the background is assigned a value of 0. Each corresponding ground truth has the same number as its respective image. For instance, the image of an oil spill has a corresponding number of 0001, as well as its ground truth. The complete dataset consists of three parts: Sentinel-1 SAR Oil spill image dataset for train, validate, and test deep learning models. Part I. (10.5281/zenodo.8346860) Sentinel-1 SAR Oil spill image dataset for train, validate, and test deep learning models. Part II. (10.5281/zenodo.8253899) Sentinel-1 SAR Oil spill image dataset for train, validate, and test deep learning models. Part III. (10.5281/zenodo.13761290)
本图像数据集为《用于深度学习模型训练、验证与测试的Sentinel-1合成孔径雷达（SAR）溢油图像数据集 第一部分》，是面向溢油检测与分割任务、用于深度学习模型训练与验证的图像数据集的首部分。 本部分仅包含溢油检测任务所需的训练与验证图像。 该数据集包含以分贝（dB）为单位的Sigma0波段Sentinel-1 SAR图像及其真值标签（ground truth）。所有输入图像尺寸均为2048×2048×2，真值标签尺寸为2048×2048，全部采用TIFF格式存储。 数据集文件的组织方式如下： 01_Train_Val_Oil_Spill_images 文件夹包含1200张以分贝为单位的Sentinel-1 SAR Sigma0波段溢油图像。 01_Train_Val_Oil_Spill_mask 文件夹包含1200张与上述Sentinel-1 SAR Sigma0波段溢油图像对应的真值标签图像，其中前景像素值设为1，背景像素值设为0。 每张图像与其对应的真值标签编号完全一致。例如，某溢油图像的编号为0001，则其对应的真值标签编号同样为0001。 完整数据集共分为三个部分： 1. 《用于深度学习模型训练、验证与测试的Sentinel-1 SAR溢油图像数据集 第一部分》(10.5281/zenodo.8346860) 2. 《用于深度学习模型训练、验证与测试的Sentinel-1 SAR溢油图像数据集 第二部分》(10.5281/zenodo.8253899) 3. 《用于深度学习模型训练、验证与测试的Sentinel-1 SAR溢油图像数据集 第三部分》(10.5281/zenodo.13761290)
