MFCA-Net: a deep learning method for semantic segmentation of remote sensing images

Semantic segmentation of remote sensing images (RSI) is an important research direction in remote sensing technology. This paper proposes a multi-feature fusion and channel attention network, MFCA-Net, aiming to improve the segmentation accuracy of remote sensing images and the recognition performance of small target objects. The architecture is built on an encoding–decoding structure. The encoding structure includes the improved MobileNet V2 (IMV2) and multi-feature dense fusion (MFDF). In IMV2, the attention mechanism is introduced twice to enhance the feature extraction capability, and the design of MFDF can obtain more dense feature sampling points and larger receptive fields. In the decoding section, three branches of shallow features of the backbone network are fused with deep features, and upsampling is performed to achieve the pixel-level classification. Comparative experimental results of the six most advanced methods effectively prove that the segmentation accuracy of the proposed network has been significantly improved. Furthermore, the recognition degree of small target objects is higher. For example, the proposed MFCA-Net achieves about 3.65–23.55% MIoU improvement on the dataset Vaihingen.