亲爱的研友该休息了!由于当前在线用户较少,发布求助请尽量完整的填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

A coarse-to-fine boundary refinement network for building footprint extraction from remote sensing imagery

计算机科学 足迹 人工智能 边界(拓扑) 分割 卷积神经网络 比例(比率) 计算机视觉 对象(语法) 像素 模式识别(心理学) 遥感 数据挖掘 地理 地图学 数学 数学分析 考古
作者
Haonan Guo,Bo Du,Liangpei Zhang,Xin Su
出处
期刊:Isprs Journal of Photogrammetry and Remote Sensing 卷期号:183: 240-252 被引量:58
标识
DOI:10.1016/j.isprsjprs.2021.11.005
摘要

Extracting building footprints from remotely sensed imagery has long been a challenging task and is not yet fully solved. Obstructions from nearby shadows or trees, varying shapes of rooftops, omission of small buildings, and varying scale of buildings hinder existing automated models for extracting sharp building boundaries. Different reasons account for these challenges. In convolutional neural network-based methods, the down-sampling operation loses spatial details of the input images; and small buildings are omitted from the high-level features. The sheltering trees and adjacent objects shadowing may cause errors since semantic information cannot be effectively preserved. Moreover, the insufficient use of multi-scale building features causes blurry edges in the predictions for buildings with complex shapes. To address these challenges, we propose a novel coarse-to-fine boundary refinement network (CBR-Net) that accurately extracts building footprints from remote sensing imagery. Unlike the existing semantic segmentation methods that directly generate building predictions at the highest level, we designed a module that progressively refines the building prediction in a coarse-to-fine manner. In this way, the advantages of both the high-level and low-level features can be retained. We also present a novel boundary refinement (BR) module that enhances the ability of the CBR-Net model to perceive and refine building edges. The BR module refines building prediction by perceiving the direction of each pixel in a remotely sensed optical image to the center of the nearest object to which it might belong. The refined results are used as pseudo labels in a self-supervision process that increases model robustness to noisy labels or obstructions. Experimental results on three public building datasets, including the WHU building dataset, the Massachusetts building dataset, and the Inria aerial image dataset, demonstrate the effectiveness of the proposed method. In evaluation tests, CBR-Net outperformed other state-of-the-art algorithms on the three datasets by maintaining both the continuous entities and accurate boundaries of buildings. The source code of the proposed CBR-Net is available at https://github.com/HaonanGuo/CBRNet.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
南宫古伦发布了新的文献求助10
4秒前
英勇幻姬发布了新的文献求助10
17秒前
cc2713206完成签到,获得积分10
23秒前
gy完成签到,获得积分10
31秒前
48秒前
隐形曼青应助永恒之光采纳,获得10
50秒前
YHY发布了新的文献求助10
52秒前
tao完成签到 ,获得积分10
55秒前
郑宏威发布了新的文献求助10
56秒前
YHY完成签到,获得积分10
59秒前
万能图书馆应助郑宏威采纳,获得10
1分钟前
英勇幻姬完成签到,获得积分10
1分钟前
安然无恙完成签到 ,获得积分10
1分钟前
郑宏威完成签到,获得积分10
1分钟前
星辰大海应助满地枫叶采纳,获得10
1分钟前
1分钟前
忍冬半夏应助SONGYEZI采纳,获得50
1分钟前
1分钟前
bai123完成签到,获得积分20
1分钟前
科研通AI2S应助科研通管家采纳,获得10
1分钟前
呆呆的猕猴桃完成签到 ,获得积分10
1分钟前
2分钟前
子平完成签到 ,获得积分10
2分钟前
永恒之光发布了新的文献求助10
2分钟前
2分钟前
gzsy完成签到 ,获得积分10
2分钟前
乐乐应助唐汉采纳,获得10
2分钟前
三三得九完成签到 ,获得积分10
2分钟前
彭于晏应助alin采纳,获得10
2分钟前
积极的尔白完成签到 ,获得积分10
2分钟前
alin完成签到,获得积分10
2分钟前
科研螺丝完成签到 ,获得积分10
2分钟前
2分钟前
2分钟前
alin发布了新的文献求助10
3分钟前
战缘1123完成签到,获得积分10
3分钟前
3分钟前
斯文的凝珍完成签到,获得积分10
3分钟前
allen完成签到,获得积分20
3分钟前
羊羊羊完成签到,获得积分10
3分钟前
高分求助中
Un calendrier babylonien des travaux, des signes et des mois: Séries iqqur îpuš 1036
Sustainable Land Management: Strategies to Cope with the Marginalisation of Agriculture 1000
Corrosion and Oxygen Control 600
Heterocyclic Stilbene and Bibenzyl Derivatives in Liverworts: Distribution, Structures, Total Synthesis and Biological Activity 500
重庆市新能源汽车产业大数据招商指南(两链两图两池两库两平台两清单两报告) 400
Division and square root. Digit-recurrence algorithms and implementations 400
行動データの計算論モデリング 強化学習モデルを例として 400
热门求助领域 (近24小时)
化学 材料科学 医学 生物 有机化学 工程类 生物化学 纳米技术 物理 内科学 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 电极 光电子学 量子力学
热门帖子
关注 科研通微信公众号,转发送积分 2545244
求助须知:如何正确求助?哪些是违规求助? 2175612
关于积分的说明 5600078
捐赠科研通 1896314
什么是DOI,文献DOI怎么找? 946171
版权声明 565327
科研通“疑难数据库(出版商)”最低求助积分说明 503541