Remote sensing image semantic segmentation network based on ENet

The current image semantic segmentation methods cannot meet the requirements of high precision and speed for remote sensing analysis. ENet network model builds a network, which has characteristics few parameters fast operation speed. attention mechanism module is integrated with model, can deeply mine features in datasets ensure accuracy segmentation. author combines to construct new model. first constructed based on simplified further improve recognition. Then, fused conduct deep orderly mining data set. It Simulations are performed three general datasets, experimental results show