MBNet: Multi-Branch Network for Extraction of Rural Homesteads Based on Aerial Images

文献类型： 外文期刊

第一作者： Wei, Ren

作者： Wei, Ren;Fan, Beilei;Wang, Yuting;Zhou, Ailian;Zhao, Zijuan;Wei, Ren;Fan, Beilei;Wang, Yuting;Zhou, Ailian;Zhao, Zijuan

作者机构：

关键词： high-resolution remote sensing images; deep learning; rural homestead; multi-branch; multi-scale features; boundary refinement

期刊名称：REMOTE SENSING （ 影响因子：5.349； 五年影响因子：5.786 ）

ISSN：

年卷期： 2022 年 14 卷 10 期

页码：

收录情况： SCI

摘要： Deep convolution neural network (DCNN) technology has achieved great success in extracting buildings from aerial images. However, the current mainstream algorithms are not satisfactory in feature extraction and classification of homesteads, especially in complex rural scenarios. This study proposes a deep convolutional neural network for rural homestead extraction consisting of a detail branch, a semantic branch, and a boundary branch, namely Multi-Branch Network (MBNet). Meanwhile, a multi-task joint loss function is designed to constrain the consistency of bounds and masks with their respective labels. Specifically, MBNet guarantees the details of prediction through serial 4x down-sampled high-resolution feature maps and adds a mixed-scale spatial attention module at the tail of the semantic branch to obtain multi-scale affinity features. At the same time, the low-resolution semantic feature maps and interaction between high-resolution detail feature maps are maintained. Finally, the result of semantic segmentation is refined by the point-to-point module (PTPM) through the generated boundary. Experiments on UAV high-resolution imagery in rural areas show that our method achieves better performance than other state-of-the-art models, which helps to refine the extraction of rural homesteads. This study demonstrates that MBNet is a potential candidate for building an automatic rural homestead management system.

分类号：

  • 相关文献
作者其他论文 更多>>

微信小程序