SIFT Based Monocular SLAM with GPU Accelerated

Tonghui Wang; Guoyun Lv; Shikai Wang; Haili Li; Baicen Lu

Communications and Networking. 12th International Conference, ChinaCom 2017, Xi’an, China, October 10-12, 2017, Proceedings, Part II

Research Article

SIFT Based Monocular SLAM with GPU Accelerated

Download

299 downloads

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.1007/978-3-319-78139-6_2,
    author={Tonghui Wang and Guoyun Lv and Shikai Wang and Haili Li and Baicen Lu},
    title={SIFT Based Monocular SLAM with GPU Accelerated},
    proceedings={Communications and Networking. 12th International Conference, ChinaCom 2017, Xi’an, China, October 10-12, 2017, Proceedings, Part II},
    proceedings_a={CHINACOM},
    year={2018},
    month={4},
    keywords={SLAM Monocular SIFT GPU 3D Reconstruction},
    doi={10.1007/978-3-319-78139-6_2}
}

Tonghui Wang
Guoyun Lv
Shikai Wang
Haili Li
Baicen Lu
Year: 2018
SIFT Based Monocular SLAM with GPU Accelerated
CHINACOM
Springer
DOI: 10.1007/978-3-319-78139-6_2

Tonghui Wang¹^,*, Guoyun Lv¹^,*, Shikai Wang¹^,*, Haili Li¹^,*, Baicen Lu¹^,*

1: Northwestern Polytechnical University

*Contact email: nwpuwth@qq.com, 178510887@qq.com, 1748710855@qq.com, 735110965@qq.com, 992159044@qq.com

Abstract

With the rapid development of computer vision technology, 3D Reconstruction based on monocular SLAM (Simultaneous Localization and Mapping) has got more and more attention for its simple requirements, low cost, easy to implement, convenient to carry. ORB-SLAM is a kind of monocular SLAM method based on feature point. ORB feature can meet the real-time requirements for SLAM, but it does not have scale invariance. In this paper, we proposed a monocular SIFT-SLAM, in which a SIFT (Scale Invariant Feature Transform) algorithm based on GPU is used to replace the ORB algorithm, to implement 3D Reconstruction. We show the experiment result of SIFT-SLAM in this paper, which gets some improvement.

Keywords: SLAM Monocular SIFT GPU 3D Reconstruction

Published: 2018-04-30
Appears in: SpringerLink

: http://dx.doi.org/10.1007/978-3-319-78139-6_2