Loading...
Please wait, while we are loading the content...
Similar Documents
Feature Residual Analysis Network for Building Extraction from Remote Sensing Images
| Content Provider | MDPI |
|---|---|
| Author | Miao, Yuqi Jiang, Shanshan Xu, Yiming Wang, Dongjie |
| Copyright Year | 2022 |
| Description | Building extraction of remote sensing images is very important for urban planning. In the field of deep learning, in order to extract more detailed building features, more complex convolution operations and larger network models are usually used to segment buildings, resulting in low efficiency of automatic extraction. The existing network is difficult to balance the extraction accuracy and extraction speed. Considering the segmentation accuracy and speed, a Feature Residual Analysis Network (FRA-Net) is proposed to realize fast and accurate building extraction. The whole network includes two stages: encoding and decoding. In the encoding stage, a Separable Residual Module (SRM) is designed to extract feature information and extract building features from remote sensing images, avoiding the use of large convolution kernels to reduce the complexity of the model. In the decoding stage, the SRM is used for information decoding, and a multi-feature attention module is constructed to enhance the effective information. The experimental results on the LandCover dataset and Massachusetts Buildings dataset show that the reasoning speed has been greatly improved without reducing the segmentation accuracy. |
| Starting Page | 5095 |
| e-ISSN | 20763417 |
| DOI | 10.3390/app12105095 |
| Journal | Applied Sciences |
| Issue Number | 10 |
| Volume Number | 12 |
| Language | English |
| Publisher | MDPI |
| Publisher Date | 2022-05-18 |
| Access Restriction | Open |
| Subject Keyword | Applied Sciences Remote Sensing Buildings Extraction Deep Learning Feature Residual Analysis Network |
| Content Type | Text |
| Resource Type | Article |
