Scan registration for underwater mechanical scanning imaging sonar using symmetrical Kullback-Leibler divergence

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 水下机器人研究室

	Scan registration for underwater mechanical scanning imaging sonar using symmetrical Kullback-Leibler divergence
	Li YP(李一平)1 ; Song SM(宋三明)1 ; Jiang M(蒋敏)1,2 ; Tang FZ(唐凤珍)1; Liu J(刘健)1 ; Feng XS(封锡盛)1
刊名	JOURNAL OF ELECTRONIC IMAGING
	2019
卷号	28 期号:1 页码:1-11
关键词	underwater robots mechanical scanning imaging sonar scan registration symmetrical Kullback-Leibler divergence
ISSN号	1017-9909
产权排序	1
英文摘要	Due to its advantages in size and energy consumption, mechanical scanning imaging sonar (MSIS) has been widely used in portable and economic underwater robots to observe the turbid and noisy underwater environment. However, handicapped by the coarseness in spatial and temporal resolution, it is difficult to stitch the scan pieces together into a panoramic map for global understanding. A registration method named symmetrical Kullback-Leibler divergence (SKLD)-distribution-to-distribution (D2D), which models each scan as a Gaussian mixture model (GMM) and evaluates the similarity between two GMMs in a D2D way with the measure defined by SKLD, is proposed to register the scans collected by MSIS. SKLD not only weights the difference between distributions with the prior probability but also increases the numerical stability with the symmetrical constraint in distance measure. Moreover, an approximation strategy is designed to derive a tractable solution for the KLD between two GMMs. Experimental results on the scans that were collected from the realistic underwater environment demonstrate that SKLD-D2D dramatically reduces the computational cost without compromising the estimation precision. (C) 2019 SPIE and IS&T
资助项目	National Key Research and Development Program of China[2016YFC0300801] ; Public Science and Technology Research Funds Projects of Ocean[201505017] ; National Natural Science Foundation of China ; National Natural Science Foundation of China[41506121] ; National Key Research and Development Program of China[2017YFC030 5901] ; National Key Research and Development Program of China[2016YFC0301601] ; Strategic Priority Program of the Chinese Academy of Sciences[XDA13030205] ; Strategic Priority Program of the Chinese Academy of Sciences[XDA11040103] ; State Key Laboratory of Robotics of China[2017-Z010] ; Natural Science Foundation of Jiangsu Province, China[BK20170558] ; project of R&D Center for Underwater Construction Robotics - Ministry of Ocean and Fisheries (MOF) ; Korea Institute of Marine Science & Technology Promotion (KIMST), Korea[PJT200539] ; National Key Research and Development Program of China ; Chinese Academy of Sciences ; State Key Laboratory of Robotics of China ; Natural Science Foundation of Jiangsu Province, China ; Ministry of Ocean and Fisheries (MOF) ; Korea Institute of Marine Science & Technology Promotion (KIMST), Korea ; Public science and technology research funds projects of ocean
WOS关键词	SLAM
WOS研究方向	Engineering ; Optics ; Imaging Science & Photographic Technology
语种	英语
WOS记录号	WOS:000460119700026
内容类型	期刊论文
源URL	[http://ir.sia.cn/handle/173321/24415]
专题	沈阳自动化研究所_水下机器人研究室
通讯作者	Song SM(宋三明)
作者单位	1.Chinese Academy of Sciences, Shenyang Institute of Automation, State Key Laboratory of Robotics, Shenyang, China 2.University of Chinese Academy of Sciences, Beijing, China
推荐引用方式 GB/T 7714	Li YP,Song SM,Jiang M,et al. Scan registration for underwater mechanical scanning imaging sonar using symmetrical Kullback-Leibler divergence[J]. JOURNAL OF ELECTRONIC IMAGING,2019,28(1):1-11.
APA	Li YP,Song SM,Jiang M,Tang FZ,Liu J,&Feng XS.(2019).Scan registration for underwater mechanical scanning imaging sonar using symmetrical Kullback-Leibler divergence.JOURNAL OF ELECTRONIC IMAGING,28(1),1-11.
MLA	Li YP,et al."Scan registration for underwater mechanical scanning imaging sonar using symmetrical Kullback-Leibler divergence".JOURNAL OF ELECTRONIC IMAGING 28.1(2019):1-11.