Real-time RGBD SLAM System

被引：2

作者：

Czuprynski, Blazej ^{[1
]}

Strupczewski, Adam ^{[1
]}

机构：

[1] Warsaw Univ Technol, PL-00661 Warsaw, Poland

来源：

PHOTONICS APPLICATIONS IN ASTRONOMY, COMMUNICATIONS, INDUSTRY, AND HIGH-ENERGY PHYSICS EXPERIMENTS 2015 | 2015年 / 9662卷

关键词：

SLAM; Tracking; Depth camera; Visual odometry; TRACKING;

D O I：

10.1117/12.2205874

中图分类号：

O43 [光学];

学科分类号：

070207 ; 0803 ;

摘要：

A real-time tracking and mapping SLAM system is presented. The developed system uses input from an RGBD sensor and tracks the camera pose from frame to frame. The tracking is based on matched feature points and is performed with respect to selected keyframes. The system is robust and scalable, as an arbitrary number of keyframes can be chosen for visualization and tracking depending on the desired accuracy and speed. The presented system is also a good platform for further research.

引用

页数：9

共 16 条

[1]

Agrawal M, 2008, LECT NOTES COMPUT SC, V5305, P102, DOI 10.1007/978-3-540-88693-8_8

[2]

Alahi A, 2012, PROC CVPR IEEE, P510, DOI 10.1109/CVPR.2012.6247715

[3]

[Anonymous], P INT C INT ROB SYST

[4]

[Anonymous], 2007, 6 IEEE ACM INT S MIX

[5]

[Anonymous], 2014, RGBD MAPPING USING D

[6]

[Anonymous], 2014, LSD SLAM LARGE SCALE

[7] Tracking people with twists and exponential maps [J].

Bregler, C ;

Malik, J .

1998 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 1998, :8-15

[8]

Jang J. S., 2008, IEEE INT C AUT FAC G

[9]

Newcombe RA, 2011, IEEE I CONF COMP VIS, P2320, DOI 10.1109/ICCV.2011.6126513

[10] KinectFusion: Real-Time Dense Surface Mapping and Tracking [J].

Newcombe, Richard A. ;

Izadi, Shahram ;

Hilliges, Otmar ;

Molyneaux, David ;

Kim, David ;

Davison, Andrew J. ;

Kohli, Pushmeet ;

Shotton, Jamie ;

Hodges, Steve ;

Fitzgibbon, Andrew .

2011 10TH IEEE INTERNATIONAL SYMPOSIUM ON MIXED AND AUGMENTED REALITY (ISMAR), 2011, :127-136

← 1 2 →