MA-Unet3+ Segmentation Network of Remote Sensing Image Based on ECA Block

Semantic segmentation is a basal task and is a typical computer vision problem. Although semantic segmentation is developing rapidly, the speed and accuracy of model segmentation still need to be further improved. For solve the issue of scale differences between target objects and loss of spatial information in the segmentation task of remote sensing images, by improving the original U-Net3+ network and introducing the attention mechanism, a new network MA-Unet3+ is constructed. In the coding phase, images of unlike scales are fused, and the full-scale connections are pruned, some skip connections are removed, and attention mechanisms are introduced between each layer. The improved model is contrast with some common network models, and the experiment achieves 78.7% average intersection (mIoU) on the Vaihingen dataset, which is 0.8% better than this optimized network U-Net3+, the average category pixel accuracy (MPA) is 92.4%, which is 1.2% better, and the similarity coefficient (Dice) result is 87.3%, which is 0.8% better. 0.8%, it is observed that MA-Unet3+ is precede other algorithms.