The Onera Satellite Change Detection dataset

Onera卫星变化检测数据集解决了检测不同日期的卫星图像之间变化的问题。它包括从Sentinel-2卫星2015年和2018拍摄的24对多光谱图像。地点遍布世界各地，在巴西，美国，欧洲，中东和亚洲。对于每个位置，提供了由Sentinel-2卫星获得的13波段多光谱卫星图像的注册对。图像的空间分辨率在10m，20m和60m之间变化。为14对图像对提供了像素级变化地面真相。带注释的变化侧重于城市变化，例如新建筑物或新道路。这些数据可用于训练和设置变化检测算法的参数。The Onera Satellite Change Detection Dataset addresses the problem of detecting changes between satellite images captured on different dates. It includes 24 pairs of multispectral images acquired by the Sentinel-2 satellite in 2015 and 2018. The covered locations span across the globe, including Brazil, the United States, Europe, the Middle East, and Asia. For each location, a registered pair of 13-band multispectral satellite images obtained by the Sentinel-2 satellite is provided. The spatial resolution of the images ranges from 10 m, 20 m to 60 m. Pixel-level change ground truth is provided for 14 of the image pairs. The annotated changes focus on urban changes such as new buildings or new roads. These data can be used for training change detection algorithms and tuning their parameters.

搜集汇总

背景与挑战

背景概述

该数据集是一个用于卫星图像变化检测的公开数据集，包含24对来自Sentinel-2卫星的多光谱图像（2015年和2018年拍摄），覆盖全球多个地区，图像具有13个波段且空间分辨率在10m至60m之间。数据集提供了14对图像的像素级变化地面真相，专注于城市变化（如新建筑或道路），适用于训练和优化变化检测算法。