Simultaneous localization and mapping using monocular direct method

Chao Meng; Baiwei Guo; Xin Liu

doi:10.1109/ICARCV.2016.7838785

Simultaneous localization and mapping using monocular direct method

Chao Meng, Baiwei Guo, Xin Liu

School of Aerospace Engineering

Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Citations (Scopus)

Abstract

In this paper, we accomplish simultaneous localization and mapping using the monocular LSD-SLAM. This method is different with feature method, estimating the accurate and reconstructing the large scale environment map. Using the direct image alignment, the environment can be mapped in pose-graph of key frames semi-dense maps. The LSD-SLAM contains two advantage. A novel direct tracking method can definitely estimate the scale-drift. In addition, the probabilistic estimation can optimize the effect of noisy depth values on tracking. The experiment showed the LSD-SLAM is reliability, robustness and real-time.

Original language	English
Title of host publication	2016 14th International Conference on Control, Automation, Robotics and Vision, ICARCV 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781509035496
DOIs	https://doi.org/10.1109/ICARCV.2016.7838785
Publication status	Published - 2016
Event	14th International Conference on Control, Automation, Robotics and Vision, ICARCV 2016 - Phuket, Thailand Duration: 13 Nov 2016 → 15 Nov 2016

Publication series

Name	2016 14th International Conference on Control, Automation, Robotics and Vision, ICARCV 2016

Conference

Conference	14th International Conference on Control, Automation, Robotics and Vision, ICARCV 2016
Country/Territory	Thailand
City	Phuket
Period	13/11/16 → 15/11/16

Keywords

LSD-SLAM
direct image alignment
probabilistic estimation
semi-dense maps

Access to Document

10.1109/ICARCV.2016.7838785

Cite this

Meng, C., Guo, B., & Liu, X. (2016). Simultaneous localization and mapping using monocular direct method. In 2016 14th International Conference on Control, Automation, Robotics and Vision, ICARCV 2016 Article 7838785 (2016 14th International Conference on Control, Automation, Robotics and Vision, ICARCV 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICARCV.2016.7838785

@inproceedings{fd31993f990046e0be04efef32f952e4,

title = "Simultaneous localization and mapping using monocular direct method",

abstract = "In this paper, we accomplish simultaneous localization and mapping using the monocular LSD-SLAM. This method is different with feature method, estimating the accurate and reconstructing the large scale environment map. Using the direct image alignment, the environment can be mapped in pose-graph of key frames semi-dense maps. The LSD-SLAM contains two advantage. A novel direct tracking method can definitely estimate the scale-drift. In addition, the probabilistic estimation can optimize the effect of noisy depth values on tracking. The experiment showed the LSD-SLAM is reliability, robustness and real-time.",

keywords = "LSD-SLAM, direct image alignment, probabilistic estimation, semi-dense maps",

author = "Chao Meng and Baiwei Guo and Xin Liu",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 14th International Conference on Control, Automation, Robotics and Vision, ICARCV 2016 ; Conference date: 13-11-2016 Through 15-11-2016",

year = "2016",

doi = "10.1109/ICARCV.2016.7838785",

language = "English",

series = "2016 14th International Conference on Control, Automation, Robotics and Vision, ICARCV 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2016 14th International Conference on Control, Automation, Robotics and Vision, ICARCV 2016",

address = "United States",

}

Meng, C, Guo, B & Liu, X 2016, Simultaneous localization and mapping using monocular direct method. in 2016 14th International Conference on Control, Automation, Robotics and Vision, ICARCV 2016., 7838785, 2016 14th International Conference on Control, Automation, Robotics and Vision, ICARCV 2016, Institute of Electrical and Electronics Engineers Inc., 14th International Conference on Control, Automation, Robotics and Vision, ICARCV 2016, Phuket, Thailand, 13/11/16. https://doi.org/10.1109/ICARCV.2016.7838785

Simultaneous localization and mapping using monocular direct method. / Meng, Chao; Guo, Baiwei; Liu, Xin.
2016 14th International Conference on Control, Automation, Robotics and Vision, ICARCV 2016. Institute of Electrical and Electronics Engineers Inc., 2016. 7838785 (2016 14th International Conference on Control, Automation, Robotics and Vision, ICARCV 2016).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Simultaneous localization and mapping using monocular direct method

AU - Meng, Chao

AU - Guo, Baiwei

AU - Liu, Xin

PY - 2016

Y1 - 2016

N2 - In this paper, we accomplish simultaneous localization and mapping using the monocular LSD-SLAM. This method is different with feature method, estimating the accurate and reconstructing the large scale environment map. Using the direct image alignment, the environment can be mapped in pose-graph of key frames semi-dense maps. The LSD-SLAM contains two advantage. A novel direct tracking method can definitely estimate the scale-drift. In addition, the probabilistic estimation can optimize the effect of noisy depth values on tracking. The experiment showed the LSD-SLAM is reliability, robustness and real-time.

AB - In this paper, we accomplish simultaneous localization and mapping using the monocular LSD-SLAM. This method is different with feature method, estimating the accurate and reconstructing the large scale environment map. Using the direct image alignment, the environment can be mapped in pose-graph of key frames semi-dense maps. The LSD-SLAM contains two advantage. A novel direct tracking method can definitely estimate the scale-drift. In addition, the probabilistic estimation can optimize the effect of noisy depth values on tracking. The experiment showed the LSD-SLAM is reliability, robustness and real-time.

KW - LSD-SLAM

KW - direct image alignment

KW - probabilistic estimation

KW - semi-dense maps

UR - http://www.scopus.com/inward/record.url?scp=85015231648&partnerID=8YFLogxK

U2 - 10.1109/ICARCV.2016.7838785

DO - 10.1109/ICARCV.2016.7838785

M3 - Conference contribution

AN - SCOPUS:85015231648

T3 - 2016 14th International Conference on Control, Automation, Robotics and Vision, ICARCV 2016

BT - 2016 14th International Conference on Control, Automation, Robotics and Vision, ICARCV 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 14th International Conference on Control, Automation, Robotics and Vision, ICARCV 2016

Y2 - 13 November 2016 through 15 November 2016

ER -

Meng C, Guo B, Liu X. Simultaneous localization and mapping using monocular direct method. In 2016 14th International Conference on Control, Automation, Robotics and Vision, ICARCV 2016. Institute of Electrical and Electronics Engineers Inc. 2016. 7838785. (2016 14th International Conference on Control, Automation, Robotics and Vision, ICARCV 2016). doi: 10.1109/ICARCV.2016.7838785

Simultaneous localization and mapping using monocular direct method

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this