Weight algorithm based depth camera point-to-plane ICP algorithm

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 工艺装备与智能机器人研究室

	Weight algorithm based depth camera point-to-plane ICP algorithm
	Zeng YJ(曾毓菁)1,2,3; Jiang Y(姜勇)2,3
	2021
会议日期	July 27-31, 2021
会议地点	Jiaxing, China
页码	799-804
英文摘要	We propose a weight algorithm to improve the accuracy and robustness of ICP algorithm. Existing methods tend to drift in scenes without sufficient geometric information. First, we propose a new weight method for ICP algorithm of point-to-plane error metric. By detecting the uncertainty of the pose, we apply a weight to each point according to the constraints of the potentially unstable transformation. our algorithm achieves accurate and robust trajectory estimation results. Secondly, we compare the most advanced weight algorithms and propose a depth value quadratic attenuation algorithm based on the measurement characteristics of consumer depth cameras. Results on the public TUM RGB-D database benchmark show that our ICP algorithm achieves state-of-the-art results in terms of accuracy. © 2021 IEEE.
源文献作者	IEEE Robotics and Automation Society ; Shenyang Institute of Automation CAS ; Shenzhen Academy of Robotics
产权排序	1
会议录	2021 IEEE 11th International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2021
会议录出版者	IEEE
会议录出版地	New York
语种	英语
ISSN号	2642-6633
ISBN号	978-1-6654-2527-8
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/29934]
专题	工艺装备与智能机器人研究室
通讯作者	Jiang Y(姜勇)
作者单位	1.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China 2.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China 3.College of Information Science and Engineering, Northeastern University, Shenyang, China
推荐引用方式 GB/T 7714	Zeng YJ,Jiang Y. Weight algorithm based depth camera point-to-plane ICP algorithm[C]. 见:. Jiaxing, China. July 27-31, 2021.