Comparison of optimized object-based RF-DT algorithm and SegNet algorithm for classifying Karst wetland vegetation communities using ultra-high spatial resolution UAV data

•Huixian Karst National Wetland is currently the most representative karst wetland in China.•Optimized RF outperforms fused SegNet classifier in coarse classification of vegetation.•RF-based classifications have significant differences from SegNet classifier using UAV images.•RF-DT algorithm achieved over 0.878 overall accuracy of karst vegetation communities.•Statistical analysis of variables’ importance for classifying karst vegetation communities.