 This article investigates object-based wetland classification using multi-feature combination of ultra-high spatial resolution multi-spectral images, MSI, from Sentinel to a data, UAV RGB images, and Google Earth RGB images. The Gram-Schmidt, GS, transformation is used to fuse the data sources, and three different feature combination classification scenarios are constructed for Fusion GE and UAV MSI, respectively, based on selected features. The object-based random forest, RF, algorithms with parameters optimization are used to carry out finer wetland classification. Results show that the Fusion of UAV images has the highest accuracy in Scenario 3, while the Fusion of GE images has the highest accuracy in Scenario 2. Both data sources reach the highest accuracy in Scenario 3. The contribution of different features to wetland classification is obtained with spectral and vegetation indexes, texture, geometric and contextual features. This article was authored by Ren Fangeng, Chuangun Jin, Bolin Fu, and others. We are article.tv, links in the description below.