Building Regional Covariance Descriptors for Vehicle Detection

doi:10.1109/LGRS.2017.2653772

	Building Regional Covariance Descriptors for Vehicle Detection
	Chen, Xueyun 1,2; Gong, Ren-Xi 1,2; Xie, Ling-Ling 1,2; Xiang, Shiming1,2 ; Liu, Cheng-Lin1,2 ; Pan, Chun-Hong1,2
刊名	IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
	2017-04-01
卷号	14 期号:4 页码:524-528
关键词	Deep Convolutional Neural Networks (Dcnns) Regional Covariance Descriptor (Rcd) Vehicle Detection
DOI	10.1109/LGRS.2017.2653772
文献子类	Article
英文摘要	We study the question of building regional covariance descriptors (RCDs) for vehicle detection from highresolution satellite images. A unified way is proposed to build RCD features by constant convolutional kernels in the forms of 2-D masks. Two novel formulas are designed to construct different RCD types based upon one or two convolutional masks, obtaining ten novel RCD features by four simple constant convolutional masks. Experiments show that such convolutional-mask- based RCDs outperform the previous image-derivative-based RCDs, the popular local binary patterns (LBPs), the histogram of oriented gradients (HOGs), and LBP+HOG. Furthermore, feeding to nonlinear support vector machines (SVMs) of two kernel types [L-1 kernel and radial basis function (RBF)], these RCDs outperform four known deep convolutional neural networks: AlexNet, GoogLeNet, CaffeNet, and LeNet, as well as their fine-tuned models by their well-trained weights of imageNet classification. Among three popular classic classifiers we have tested in the experiments, nonlinear SVMs outperform BP and Adaboost obviously, and L-1 kernel exceeds RBF slightly.
WOS关键词	CLASSIFICATION ; IMAGES
WOS研究方向	Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology
语种	英语
WOS记录号	WOS:000399952000012
资助机构	National Natural Science Foundation of China(61661006 ; 61561007 ; 91646207)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/15271]
专题	自动化研究所_空天信息研究中心
作者单位	1.Guangxi Univ, Nanning 530004, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Chen, Xueyun,Gong, Ren-Xi,Xie, Ling-Ling,et al. Building Regional Covariance Descriptors for Vehicle Detection[J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,2017,14(4):524-528.
APA	Chen, Xueyun,Gong, Ren-Xi,Xie, Ling-Ling,Xiang, Shiming,Liu, Cheng-Lin,&Pan, Chun-Hong.(2017).Building Regional Covariance Descriptors for Vehicle Detection.IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,14(4),524-528.
MLA	Chen, Xueyun,et al."Building Regional Covariance Descriptors for Vehicle Detection".IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 14.4(2017):524-528.