SCE-Net: Self- and Cross-Enhancement Network for Single-View Height Estimation and Semantic Segmentation

Single-view height estimation and semantic segmentation have received increasing attention in recent years and play an important role in the photogrammetry and remote sensing communities. The height information and semantic information of images are correlated, and some recent works have shown that...

Full description

Saved in:
Bibliographic Details
Published in:Remote sensing (Basel, Switzerland) Switzerland), 2022-05, Vol.14 (9), p.2252
Main Authors: Xing, Siyuan, Dong, Qiulei, Hu, Zhanyi
Format: Article
Language:English
Subjects:
convolutional neural networks
Datasets
Deep learning
deep metric learning
Feature extraction
height estimation
Image processing
Image segmentation
Learning
multi-task learning
Neural networks
Photogrammetry
Remote sensing
Representations
Semantic segmentation
Semantics
single aerial image
Teaching methods
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Single-view height estimation and semantic segmentation have received increasing attention in recent years and play an important role in the photogrammetry and remote sensing communities. The height information and semantic information of images are correlated, and some recent works have shown that multi-task learning methods can achieve complementation of task-related features and improve the prediction results of the multiple tasks. Although much progress has been made in recent works, how to effectively extract and fuse height features and semantic features is still an open issue. In this paper, a self- and cross-enhancement network (SCE-Net) is proposed to jointly perform height estimation and semantic segmentation on single aerial images. A feature separation–fusion module is constructed to effectively separate and fuse height features and semantic features based on an attention mechanism for feature representation enhancement across tasks. In addition, a height-guided feature distance loss and a semantic-guided feature distance loss are designed based on deep metric learning to achieve task-aware feature representation enhancement. Extensive experiments are conducted on the Vaihingen dataset and the Potsdam dataset to verify the effectiveness of the proposed method. The experimental results demonstrate that the proposed SCE-Net could outperform the state-of-the-art methods and achieve better performance in both height estimation and semantic segmentation.
ISSN:2072-4292
2072-4292
DOI:10.3390/rs14092252