Change detection with absolute difference of multiscale deep features

doi:10.1016/j.neucom.2020.08.027

	Change detection with absolute difference of multiscale deep features
	Huang, Rui 1,2; Zhou, Mo 1; Zhao, Qiang 3; Zou, Yaobin 2
	2020-12-22
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
卷号	418 页码:102-113
摘要	Most of the previous change detection methods are designed based on the difference of two images. However, directly using intensity or the features to generate difference image may be easily affected by the illumination and camera pose variations. In this paper, we show that accurate change detection results can be obtained by fusing the absolute difference of multiscale deep features of the reference and query images. Specifically, we build a change detection network, which computes absolute difference of the multiscale deep features of image pairs and learns adaptive features for change detection. The pro-posed network is based on off-the-shelf CNNs, whose convolutional layer blocks are used as feature extracting modules to extract multiscale deep features. We devise intra and cross encoding modules. The intra encoding modules are used for learning change related features from extracted features. These features are used for generating absolute difference features (ADFs). By progressively fusing the ADFs from high to low layers with cross encoding modules, we obtain full resolution of change detection result. Extensive experiments on three change detection benchmark datasets validate the superiority and effectiveness of the proposed method over the state-of-the-art change detection methods. (c) 2020 Elsevier B.V. All rights reserved.
关键词	Change detection Absolute difference Deep learning Multiscale
DOI	10.1016/j.neucom.2020.08.027
收录类别	SCI
语种	英语
资助项目	Scientific research project of Tianjin Education Commission[2019KJ126] ; Natural Science Foundation of Tianjin[18JCQNJC00400] ; Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering[2018SDSJ02]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000589911100009
出版者	ELSEVIER
引用统计	被引频次：10[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/16080
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Huang, Rui
作者单位	1.Civil Aviat Univ China, Sch Comp Sci & Technol, Tianjin 300300, Peoples R China 2.China Three Gorges Univ, Hubei Key Lab Intelligent Vision Based Monitoring, Yichang 443002, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Huang, Rui,Zhou, Mo,Zhao, Qiang,et al. Change detection with absolute difference of multiscale deep features[J]. NEUROCOMPUTING,2020,418:102-113.
APA	Huang, Rui,Zhou, Mo,Zhao, Qiang,&Zou, Yaobin.(2020).Change detection with absolute difference of multiscale deep features.NEUROCOMPUTING,418,102-113.
MLA	Huang, Rui,et al."Change detection with absolute difference of multiscale deep features".NEUROCOMPUTING 418(2020):102-113.