ReA-Net: A Multiscale Region Attention Network With Neighborhood Consistency Supervision for Building Extraction From Remote Sensing Image

ReA-Net: A Multiscale Region Attention Network With Neighborhood Consistency Supervision for Building Extraction From Remote Sensing Image

Aimed at the challenge of low accuracy of building segmentation caused by poor continuity of remote-sensing-image regions and blurred boundaries, a remote sensing building semantics segmentation algorithm based on multiscale regional consistent attention supervision is proposed. First, based on the...

Full description

Bibliographic Details
Main Authors: Shengjun Xu, Bowen Deng, Yuebo Meng, Guanghui Liu, Jiuqiang Han
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Building segmentation
neighborhood consistency supervision
region attention
remote sensing image
U-Net
Online Access:https://ieeexplore.ieee.org/document/9878196/

Internet

https://ieeexplore.ieee.org/document/9878196/

Similar Items