A fast Reconstruction Method of 3D Object Point Cloud Based on Realsense D435
被引:0
作者:
Ma, Wenyuan
论文数: 0引用数: 0
h-index: 0
机构:
Beijing Univ Chem Technol, Coll Int Educ, Beijing, Peoples R ChinaBeijing Univ Chem Technol, Coll Int Educ, Beijing, Peoples R China
Ma, Wenyuan
[1
]
Yang, Kehan
论文数: 0引用数: 0
h-index: 0
机构:
Univ Detroit Mercy, Coll Engn & Sci, Detroit, MI 48221 USABeijing Univ Chem Technol, Coll Int Educ, Beijing, Peoples R China
Yang, Kehan
[2
]
机构:
[1] Beijing Univ Chem Technol, Coll Int Educ, Beijing, Peoples R China
[2] Univ Detroit Mercy, Coll Engn & Sci, Detroit, MI 48221 USA
来源:
PROCEEDINGS OF THE 39TH CHINESE CONTROL CONFERENCE
|
2020年
关键词:
3D Reconstruction;
Depth Camera;
point cloud;
manually feature points;
D O I:
暂无
中图分类号:
TP [自动化技术、计算机技术];
学科分类号:
0812 ;
摘要:
In order to achieve the fast and effective 3D reconstruction, this paper proposes a method of 3D reconstruction system based on depth camera Realsense D435. On one hand, as the traditional methods in extracting feature points have some difficulties in distinguishing the feature points on texture-less objects, this paper adopts a special method that designs the feature points independently, with use the cheap deep camera achieving the 3D reconstruction based on the manually feature points. On the other hand, this paper adopt a global registration strategy to reduce the phenomenon of error accumulation.