Simultaneous Change Region and Change Pattern Identification for Very High Resolution Images

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 先进时空数据分析与学习

	Simultaneous Change Region and Change Pattern Identification for Very High Resolution Images
	Huo CL(霍春雷); Huo CL(霍春雷)
发表期刊	Journal of Applied Remote Sensing
	2017
卷号	1 期号:1 页码:1-10
摘要	By taking advantages of fine details obtained by the improved spatial resolution, very high resolution images are promising for detecting change regions and identifying change patterns. However, high overlaps between different change patterns and the complexities of multi-class classification make it difficult to reliably separating change features. In this paper, a framework is proposed for simultaneously detecting change regions and identifying change patterns, whose components are aimed at capturing overlaps between change patterns and reducing overlaps driven by user-specific interests. To validate the effectiveness of the proposed framework, a supervised approach is illustrated within this framework, which starts with modeling the relationship between change features by interclass couples and intraclass couples, followed by metric learning where structural sparsity is captured by the mixed norm. Experiments demonstrate the effectiveness of the proposed approach.
关键词	Change Detection Change Pattern Feature Classification Feature Learning Distance Tuning.
收录类别	SCI
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/15385
专题	多模态人工智能系统全国重点实验室_先进时空数据分析与学习
通讯作者	Huo CL(霍春雷)
作者单位	中国科学院自动化研究所模式识别国家重点实验室
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	Huo CL,Huo CL. Simultaneous Change Region and Change Pattern Identification for Very High Resolution Images[J]. Journal of Applied Remote Sensing,2017,1(1):1-10.
APA	Huo CL,&霍春雷.(2017).Simultaneous Change Region and Change Pattern Identification for Very High Resolution Images.Journal of Applied Remote Sensing,1(1),1-10.
MLA	Huo CL,et al."Simultaneous Change Region and Change Pattern Identification for Very High Resolution Images".Journal of Applied Remote Sensing 1.1(2017):1-10.

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
article.pdf（11029KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览