首页|New Remote Sensing Research from University of Tehran Described (Integration of Sentinel-1 and Sentinel-2 Data for Ground Truth Sample Migration for Multi-Tempo ral Land Cover Mapping)
New Remote Sensing Research from University of Tehran Described (Integration of Sentinel-1 and Sentinel-2 Data for Ground Truth Sample Migration for Multi-Tempo ral Land Cover Mapping)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News - Investigators publish new report on re mote sensing. According to news reporting from Tehran, Iran, by NewsRx journalis ts, research stated, “Reliable and up-to-date training reference samples are imp erative for land cover (LC) classification. However, such training datasets are not always available in practice.” The news correspondents obtained a quote from the research from University of Te hran: “The sample migration method has shown remarkable success in addressing th is challenge in recent years. This work investigated the application of Sentinel -1 (S1) and Sentinel-2 (S2) data in training sample migration. In addition, the impact of various spectral bands and polarizations on the accuracy of the migrat ed training samples was also assessed. Subsequently, combined S1 and S2 images w ere classified using the Support Vector Machines (SVM) and Random Forest (RF) cl assifiers to produce annual LC maps from 2017 to 2021. The results showed a high er accuracy (98.25%) in training sample migrations using both image s in comparison to using S1 (87.68%) and S2 (96.82%) d ata independently. Among the LC classes, the highest accuracy in migrated traini ng samples was found for water, built-up, bare land, grassland, cropland, and we tland.”
University of TehranTehranIranAsiaRemote SensingTechnology
NETL
NSTL
