Automatic Building Extraction from Google Earth Images under Complex Backgrounds Based on Deep Instance Segmentation Network

Automatic Building Extraction from Google Earth Images under Complex Backgrounds Based on Deep Instance Segmentation Network

Building damage accounts for a high percentage of post-natural disaster assessment. Extracting buildings from optical remote sensing images is of great significance for natural disaster reduction and assessment. Traditional methods mainly are semi-automatic methods which require human-computer inter...

Full description

Bibliographic Details
Main Authors: Qi Wen, Kaiyu Jiang, Wei Wang, Qingjie Liu, Qing Guo, Lingling Li, Ping Wang
Format: Article
Language:English
Published: MDPI AG 2019-01-01
Series:Sensors
Subjects:
building extraction
deep learning
Mask R-CNN
rotation bounding box
receptive field block
instance segmentation
Online Access:http://www.mdpi.com/1424-8220/19/2/333

Internet

http://www.mdpi.com/1424-8220/19/2/333

Similar Items