CG-Net: Conditional GIS-Aware Network for Individual Building Segmentation in VHR SAR Images

计算机科学 合成孔径雷达 足迹 基本事实 分割 人工智能 图像分割 遥感 计算机视觉 比例(比率) 地理信息系统 数据挖掘 地理 地图学 考古
作者
Yeneng Sun,Yuansheng Hua,Lichao Mou,Xiao Xiang Zhu
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:60: 1-15 被引量:29
标识
DOI:10.1109/tgrs.2020.3043089
摘要

Object retrieval and reconstruction from very-high-resolution (VHR) synthetic aperture radar (SAR) images are of great importance for urban SAR applications, yet highly challenging due to the complexity of SAR data. This article addresses the issue of individual building segmentation from a single VHR SAR image in large-scale urban areas. To achieve this, we introduce building footprints from geographic information system (GIS) data as a complementary information and propose a novel conditional GIS-aware network (CG-Net). The proposed model learns multilevel visual features and employs building footprints to normalize the features for predicting building masks in the SAR image. We validate our method using a high-resolution spotlight TerraSAR-X image collected over Berlin. Experimental results show that the proposed CG-Net effectively brings improvements with variant backbones. We further compare two representations of building footprints, namely, complete building footprints and sensor-visible footprint segments, for our task, and conclude that the use of the former leads to better segmentation results. Moreover, we investigate the impact of inaccurate GIS data on our CG-Net, and this study shows that CG-Net is robust against positioning errors in the GIS data. In addition, we propose an approach of ground truth generation of buildings from an accurate digital elevation model (DEM), which can be used to generate large-scale SAR image data sets. The segmentation results can be applied to reconstruct 3-D building models at level-of-detail (LoD) 1, which is demonstrated in our experiments.
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
PDF的下载单位、IP信息已删除 (2025-6-4)

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
Mason完成签到,获得积分10
1秒前
yizhe发布了新的文献求助10
1秒前
JamesPei应助zzzz采纳,获得10
2秒前
英俊的铭应助aa采纳,获得30
2秒前
xiaohuhuan完成签到,获得积分10
2秒前
bulingbuling完成签到 ,获得积分10
3秒前
一颗小纽扣完成签到,获得积分10
4秒前
席涑完成签到,获得积分10
5秒前
CipherSage应助拼搏的婷冉采纳,获得10
5秒前
luoluo完成签到 ,获得积分10
6秒前
6秒前
醋炒栗子仁完成签到,获得积分10
6秒前
墨尔根戴青完成签到,获得积分10
7秒前
瑾瑜完成签到,获得积分10
8秒前
文小杰完成签到,获得积分10
8秒前
山月完成签到,获得积分10
9秒前
CodeCraft应助研友_LOK59L采纳,获得10
9秒前
9秒前
10秒前
欣慰妙海完成签到 ,获得积分20
10秒前
CodeCraft应助zhaopeipei采纳,获得10
10秒前
LIUYONG发布了新的文献求助10
11秒前
lin发布了新的文献求助10
13秒前
14秒前
九湖夷上完成签到 ,获得积分10
14秒前
噼里啪啦完成签到 ,获得积分10
15秒前
大个应助hahaha123213123采纳,获得30
15秒前
15秒前
惊天大幂幂完成签到,获得积分10
15秒前
英姑应助Fang Xianxin采纳,获得10
16秒前
宋老师发布了新的文献求助30
16秒前
王洋完成签到,获得积分10
17秒前
lw777完成签到,获得积分20
17秒前
慢慢完成签到,获得积分10
17秒前
18秒前
靖123456发布了新的文献求助10
18秒前
拓跋箴完成签到,获得积分10
18秒前
彭于晏应助zy采纳,获得10
19秒前
精明玲完成签到 ,获得积分10
20秒前
20秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
Research on Disturbance Rejection Control Algorithm for Aerial Operation Robots 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 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 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4038388
求助须知:如何正确求助?哪些是违规求助? 3576106
关于积分的说明 11374447
捐赠科研通 3305798
什么是DOI,文献DOI怎么找? 1819322
邀请新用户注册赠送积分活动 892672
科研通“疑难数据库(出版商)”最低求助积分说明 815029