Building Extraction from Remote Sensing Images via an Uncertainty-Aware Network

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: He, Wei, Li, Jiepan, Cao, Weinan, Zhang, Liangpei, Zhang, Hongyan
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912224722812928
author He, Wei
Li, Jiepan
Cao, Weinan
Zhang, Liangpei
Zhang, Hongyan
author_facet He, Wei
Li, Jiepan
Cao, Weinan
Zhang, Liangpei
Zhang, Hongyan
contents Building extraction aims to segment building pixels from remote sensing images and plays an essential role in many applications, such as city planning and urban dynamic monitoring. Over the past few years, deep learning methods with encoder-decoder architectures have achieved remarkable performance due to their powerful feature representation capability. Nevertheless, due to the varying scales and styles of buildings, conventional deep learning models always suffer from uncertain predictions and cannot accurately distinguish the complete footprints of the building from the complex distribution of ground objects, leading to a large degree of omission and commission. In this paper, we realize the importance of uncertain prediction and propose a novel and straightforward Uncertainty-Aware Network (UANet) to alleviate this problem. To verify the performance of our proposed UANet, we conduct extensive experiments on three public building datasets, including the WHU building dataset, the Massachusetts building dataset, and the Inria aerial image dataset. Results demonstrate that the proposed UANet outperforms other state-of-the-art algorithms by a large margin.
format Preprint
id arxiv_https___arxiv_org_abs_2307_12309
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Building Extraction from Remote Sensing Images via an Uncertainty-Aware Network
He, Wei
Li, Jiepan
Cao, Weinan
Zhang, Liangpei
Zhang, Hongyan
Computer Vision and Pattern Recognition
Building extraction aims to segment building pixels from remote sensing images and plays an essential role in many applications, such as city planning and urban dynamic monitoring. Over the past few years, deep learning methods with encoder-decoder architectures have achieved remarkable performance due to their powerful feature representation capability. Nevertheless, due to the varying scales and styles of buildings, conventional deep learning models always suffer from uncertain predictions and cannot accurately distinguish the complete footprints of the building from the complex distribution of ground objects, leading to a large degree of omission and commission. In this paper, we realize the importance of uncertain prediction and propose a novel and straightforward Uncertainty-Aware Network (UANet) to alleviate this problem. To verify the performance of our proposed UANet, we conduct extensive experiments on three public building datasets, including the WHU building dataset, the Massachusetts building dataset, and the Inria aerial image dataset. Results demonstrate that the proposed UANet outperforms other state-of-the-art algorithms by a large margin.
title Building Extraction from Remote Sensing Images via an Uncertainty-Aware Network
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2307.12309