Semantic labeling of high-resolution aerial images using an ensemble of fully convolutional networks

doi:10.1117/1.JRS.11.042617

	Semantic labeling of high-resolution aerial images using an ensemble of fully convolutional networks
	Sun, Xiaofeng1,2 ; Shen, Shuhan1,2 ; Lin, Xiangguo 3; Hu, Zhanyi1,2
发表期刊	JOURNAL OF APPLIED REMOTE SENSING
	2017-12-05
卷号	11 期号:4 页码:042617 1-18
文章类型	Article
摘要	High-resolution remote sensing data classification has been a challenging and promising research topic in the community of remote sensing. In recent years, with the rapid advances of deep learning, remarkable progress has been made in this field, which facilitates a transition from hand-crafted features designing to an automatic end-to-end learning. A deep fully convolutional networks (FCNs) based ensemble learning method is proposed to label the high-resolution aerial images. To fully tap the potentials of FCNs, both the Visual Geometry Group network and a deeper residual network, ResNet, are employed. Furthermore, to enlarge training samples with diversity and gain better generalization, in addition to the commonly used data augmentation methods (e.g., rotation, multiscale, and aspect ratio) in the literature, aerial images from other datasets are also collected for cross-scene learning. Finally, we combine these learned models to form an effective FCN ensemble and refine the results using a fully connected conditional random field graph model. Experiments on the ISPRS 2-D Semantic Labeling Contest dataset show that our proposed end-to-end classification method achieves an overall accuracy of 90.7%, a state-of-the-art in the field. (C) 2017 Society of Photo-Optical Instrumentation Engineers (SPIE)
关键词	Semantic Labeling Fully Convolutional Network Aerial Images Convolutional Neural Network Ensemble Learning
WOS标题词	Science & Technology ; Life Sciences & Biomedicine ; Technology
DOI	10.1117/1.JRS.11.042617
关键词[WOS]	CLASSIFICATION
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(61333015 ; 41371405 ; 61632003 ; 61421004)
WOS研究方向	Environmental Sciences & Ecology ; Remote Sensing ; Imaging Science & Photographic Technology
WOS类目	Environmental Sciences ; Remote Sensing ; Imaging Science & Photographic Technology
WOS记录号	WOS:000417288700001
引用统计	被引频次：11[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/21737
专题	多模态人工智能系统全国重点实验室_机器人视觉
作者单位	1.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Chinese Acad Surveying & Mapping, Inst Photogrammetry & Remote Sensing, Beijing, Peoples R China
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Sun, Xiaofeng,Shen, Shuhan,Lin, Xiangguo,et al. Semantic labeling of high-resolution aerial images using an ensemble of fully convolutional networks[J]. JOURNAL OF APPLIED REMOTE SENSING,2017,11(4):042617 1-18.
APA	Sun, Xiaofeng,Shen, Shuhan,Lin, Xiangguo,&Hu, Zhanyi.(2017).Semantic labeling of high-resolution aerial images using an ensemble of fully convolutional networks.JOURNAL OF APPLIED REMOTE SENSING,11(4),042617 1-18.
MLA	Sun, Xiaofeng,et al."Semantic labeling of high-resolution aerial images using an ensemble of fully convolutional networks".JOURNAL OF APPLIED REMOTE SENSING 11.4(2017):042617 1-18.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
JARS17.pdf（6923KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载