Robust and fast mapping based on direct methods

Pengfei Wang; Chao Gao; Wei Guo; Mantian Li; Fusheng Zha; Yanjie Cong

doi:10.1109/ICARM.2017.8273229

Robust and fast mapping based on direct methods

Pengfei Wang
, Chao Gao
, Wei Guo^*
, Mantian Li
, Fusheng Zha
, Yanjie Cong

^*Corresponding author for this work

School of Mechatronics Engineering

Harbin Institute of Technology
Double Coin Group (Jiangsu) Tyre Co.,Ltd

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

2 Scopus citations

Abstract

Simultaneous localization and mapping technology is the key technology of robot. It's now still challenging due to huge computational cost, rapid motion, non-texture environment, illumination fluctuations, etc. In this paper, we propose a SLAM algorithm based on direct method similar to LSD SLAM. In our method, we adopt constant-velocity motion model to predict the camera pose of next frame and we demonstrate the model's function on avoiding tracking lost. Besides, we adopt inverse compositional method rather than forward additive method used by LSD SLAM to align image and experiments show that ours is more efficient. In addition, we optimize the map on Sim(3) to avoid scale-drift of monocular SLAM.

Original language	English
Title of host publication	2017 2nd International Conference on Advanced Robotics and Mechatronics, ICARM 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	592-595
Number of pages	4
ISBN (Electronic)	9781538632604
DOIs	https://doi.org/10.1109/ICARM.2017.8273229
State	Published - 2 Jul 2017
Event	2nd International Conference on Advanced Robotics and Mechatronics, ICARM 2017 - Hefei and Tai'an, China Duration: 27 Aug 2017 → 31 Aug 2017

Publication series

Name	2017 2nd International Conference on Advanced Robotics and Mechatronics, ICARM 2017
Volume	2018-January

Conference

Conference	2nd International Conference on Advanced Robotics and Mechatronics, ICARM 2017
Country/Territory	China
City	Hefei and Tai'an
Period	27/08/17 → 31/08/17

Keywords

Sim(3)
direct methods
monocular SLAM
simultaneous localization and lapping
tracking

Access to Document

10.1109/ICARM.2017.8273229

Cite this

Wang, P., Gao, C., Guo, W., Li, M., Zha, F., & Cong, Y. (2017). Robust and fast mapping based on direct methods. In 2017 2nd International Conference on Advanced Robotics and Mechatronics, ICARM 2017 (pp. 592-595). (2017 2nd International Conference on Advanced Robotics and Mechatronics, ICARM 2017; Vol. 2018-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICARM.2017.8273229

@inproceedings{1ad86071cb124506ad8186d4a8c65902,

title = "Robust and fast mapping based on direct methods",

abstract = "Simultaneous localization and mapping technology is the key technology of robot. It's now still challenging due to huge computational cost, rapid motion, non-texture environment, illumination fluctuations, etc. In this paper, we propose a SLAM algorithm based on direct method similar to LSD SLAM. In our method, we adopt constant-velocity motion model to predict the camera pose of next frame and we demonstrate the model's function on avoiding tracking lost. Besides, we adopt inverse compositional method rather than forward additive method used by LSD SLAM to align image and experiments show that ours is more efficient. In addition, we optimize the map on Sim(3) to avoid scale-drift of monocular SLAM.",

keywords = "Sim(3), direct methods, monocular SLAM, simultaneous localization and lapping, tracking",

author = "Pengfei Wang and Chao Gao and Wei Guo and Mantian Li and Fusheng Zha and Yanjie Cong",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 2nd International Conference on Advanced Robotics and Mechatronics, ICARM 2017 ; Conference date: 27-08-2017 Through 31-08-2017",

year = "2017",

month = jul,

day = "2",

doi = "10.1109/ICARM.2017.8273229",

language = "英语",

series = "2017 2nd International Conference on Advanced Robotics and Mechatronics, ICARM 2017",

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

pages = "592--595",

booktitle = "2017 2nd International Conference on Advanced Robotics and Mechatronics, ICARM 2017",

address = "美国",

}

Wang, P, Gao, C, Guo, W, Li, M, Zha, F & Cong, Y 2017, Robust and fast mapping based on direct methods. in 2017 2nd International Conference on Advanced Robotics and Mechatronics, ICARM 2017. 2017 2nd International Conference on Advanced Robotics and Mechatronics, ICARM 2017, vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 592-595, 2nd International Conference on Advanced Robotics and Mechatronics, ICARM 2017, Hefei and Tai'an, China, 27/08/17. https://doi.org/10.1109/ICARM.2017.8273229

Robust and fast mapping based on direct methods. / Wang, Pengfei; Gao, Chao; Guo, Wei et al.
2017 2nd International Conference on Advanced Robotics and Mechatronics, ICARM 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 592-595 (2017 2nd International Conference on Advanced Robotics and Mechatronics, ICARM 2017; Vol. 2018-January).

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

TY - GEN

T1 - Robust and fast mapping based on direct methods

AU - Wang, Pengfei

AU - Gao, Chao

AU - Guo, Wei

AU - Li, Mantian

AU - Zha, Fusheng

AU - Cong, Yanjie

PY - 2017/7/2

Y1 - 2017/7/2

N2 - Simultaneous localization and mapping technology is the key technology of robot. It's now still challenging due to huge computational cost, rapid motion, non-texture environment, illumination fluctuations, etc. In this paper, we propose a SLAM algorithm based on direct method similar to LSD SLAM. In our method, we adopt constant-velocity motion model to predict the camera pose of next frame and we demonstrate the model's function on avoiding tracking lost. Besides, we adopt inverse compositional method rather than forward additive method used by LSD SLAM to align image and experiments show that ours is more efficient. In addition, we optimize the map on Sim(3) to avoid scale-drift of monocular SLAM.

AB - Simultaneous localization and mapping technology is the key technology of robot. It's now still challenging due to huge computational cost, rapid motion, non-texture environment, illumination fluctuations, etc. In this paper, we propose a SLAM algorithm based on direct method similar to LSD SLAM. In our method, we adopt constant-velocity motion model to predict the camera pose of next frame and we demonstrate the model's function on avoiding tracking lost. Besides, we adopt inverse compositional method rather than forward additive method used by LSD SLAM to align image and experiments show that ours is more efficient. In addition, we optimize the map on Sim(3) to avoid scale-drift of monocular SLAM.

KW - Sim(3)

KW - direct methods

KW - monocular SLAM

KW - simultaneous localization and lapping

KW - tracking

UR - https://www.scopus.com/pages/publications/85050739194

U2 - 10.1109/ICARM.2017.8273229

DO - 10.1109/ICARM.2017.8273229

M3 - 会议稿件

AN - SCOPUS:85050739194

T3 - 2017 2nd International Conference on Advanced Robotics and Mechatronics, ICARM 2017

SP - 592

EP - 595

BT - 2017 2nd International Conference on Advanced Robotics and Mechatronics, ICARM 2017

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2nd International Conference on Advanced Robotics and Mechatronics, ICARM 2017

Y2 - 27 August 2017 through 31 August 2017

ER -

Wang P, Gao C, Guo W, Li M, Zha F, Cong Y. Robust and fast mapping based on direct methods. In 2017 2nd International Conference on Advanced Robotics and Mechatronics, ICARM 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 592-595. (2017 2nd International Conference on Advanced Robotics and Mechatronics, ICARM 2017). doi: 10.1109/ICARM.2017.8273229

Robust and fast mapping based on direct methods

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this