Active Object Recognition Based on Prior Feature Distribution Table

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 光电信息技术研究室

	Active Object Recognition Based on Prior Feature Distribution Table
	Sun HB(孙海波)1,3,4; Zhu F(朱枫)3,4; Hao YM(郝颖明)3,4; Fu SF(付双飞)3,4; Kong YZ(孔研自)3,4; Xu CL(徐成龙)1
	2020
会议日期	November 27-28, 2020
会议地点	Harbin, China
关键词	Active object recognition Prior feature distribution table Feature decision tree Next best viewpoint
页码	1012-1017
英文摘要	In this paper, an active object recognition (AOR) method based on a prior feature distribution table (PFDT) is proposed. According to the distribution information of predetermined features on each object in the model base, the prior feature distribution table is created. Taking it as input, a feature decision tree (FDT) is constructed for object recognition and viewpoint planning (VP). To determine the next best viewpoint, we transform it into an optimization problem that is solved with the tree dynamic programming algorithm. Experiments show that the proposed method can achieve the object recognition task with the minimum average number of viewpoints.
产权排序	1
会议录	2020 3rd International Conference on Unmanned Systems (ICUS)
会议录出版者	IEEE
会议录出版地	New York
语种	英语
ISBN号	978-1-7281-8025-0
WOS记录号	WOS:000648775600176
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/27999]
专题	沈阳自动化研究所_光电信息技术研究室
通讯作者	Sun HB(孙海波)
作者单位	1.Northeastern University, Shenyang, China 2.University of Chinese Academy of Sciences, Shenyang, China 3.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China 4.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China
推荐引用方式 GB/T 7714	Sun HB,Zhu F,Hao YM,et al. Active Object Recognition Based on Prior Feature Distribution Table[C]. 见:. Harbin, China. November 27-28, 2020.