CUDA-Based Computation for Visual Odometry

Shen Ho Liu, Chen-Chien James Hsu, Wei Yen Wang, Cheng Hung Lin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

An enhanced visual odometry (VO) system is proposed to improve the accuracy of pose estimation based on a corrected model, and the matching algorithm is implemented on graphical processing units (GPUs) so that the computation can be accelerated in parallel and in real-time using the compute unified device architecture (CUDA) programming model. To evaluate the performance of the proposed approach, an ASUS Xtion 3D camera, laptop, and NVIDIA TX2 are employed to conduct extensive experiments. The experimental results show that compared with the traditional VO algorithm, the proposed approach gives better results over the traditional VO algorithm.

Original languageEnglish
Title of host publication2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages55-56
Number of pages2
ISBN (Electronic)9781538663097
DOIs
Publication statusPublished - 2018 Dec 12
Event7th IEEE Global Conference on Consumer Electronics, GCCE 2018 - Nara, Japan
Duration: 2018 Oct 92018 Oct 12

Publication series

Name2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018

Other

Other7th IEEE Global Conference on Consumer Electronics, GCCE 2018
CountryJapan
CityNara
Period18/10/918/10/12

Fingerprint

programming
Cameras
cameras
Processing
Experiments

Keywords

  • CUDA
  • GPU
  • Visual odometry

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Electrical and Electronic Engineering
  • Safety, Risk, Reliability and Quality
  • Instrumentation

Cite this

Liu, S. H., Hsu, C-C. J., Wang, W. Y., & Lin, C. H. (2018). CUDA-Based Computation for Visual Odometry. In 2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018 (pp. 55-56). [8574869] (2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GCCE.2018.8574869

CUDA-Based Computation for Visual Odometry. / Liu, Shen Ho; Hsu, Chen-Chien James; Wang, Wei Yen; Lin, Cheng Hung.

2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 55-56 8574869 (2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Liu, SH, Hsu, C-CJ, Wang, WY & Lin, CH 2018, CUDA-Based Computation for Visual Odometry. in 2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018., 8574869, 2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018, Institute of Electrical and Electronics Engineers Inc., pp. 55-56, 7th IEEE Global Conference on Consumer Electronics, GCCE 2018, Nara, Japan, 18/10/9. https://doi.org/10.1109/GCCE.2018.8574869
Liu SH, Hsu C-CJ, Wang WY, Lin CH. CUDA-Based Computation for Visual Odometry. In 2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 55-56. 8574869. (2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018). https://doi.org/10.1109/GCCE.2018.8574869
Liu, Shen Ho ; Hsu, Chen-Chien James ; Wang, Wei Yen ; Lin, Cheng Hung. / CUDA-Based Computation for Visual Odometry. 2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 55-56 (2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018).
@inproceedings{9397d959a3554602abda2ebd3aad05a0,
title = "CUDA-Based Computation for Visual Odometry",
abstract = "An enhanced visual odometry (VO) system is proposed to improve the accuracy of pose estimation based on a corrected model, and the matching algorithm is implemented on graphical processing units (GPUs) so that the computation can be accelerated in parallel and in real-time using the compute unified device architecture (CUDA) programming model. To evaluate the performance of the proposed approach, an ASUS Xtion 3D camera, laptop, and NVIDIA TX2 are employed to conduct extensive experiments. The experimental results show that compared with the traditional VO algorithm, the proposed approach gives better results over the traditional VO algorithm.",
keywords = "CUDA, GPU, Visual odometry",
author = "Liu, {Shen Ho} and Hsu, {Chen-Chien James} and Wang, {Wei Yen} and Lin, {Cheng Hung}",
year = "2018",
month = "12",
day = "12",
doi = "10.1109/GCCE.2018.8574869",
language = "English",
series = "2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "55--56",
booktitle = "2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018",

}

TY - GEN

T1 - CUDA-Based Computation for Visual Odometry

AU - Liu, Shen Ho

AU - Hsu, Chen-Chien James

AU - Wang, Wei Yen

AU - Lin, Cheng Hung

PY - 2018/12/12

Y1 - 2018/12/12

N2 - An enhanced visual odometry (VO) system is proposed to improve the accuracy of pose estimation based on a corrected model, and the matching algorithm is implemented on graphical processing units (GPUs) so that the computation can be accelerated in parallel and in real-time using the compute unified device architecture (CUDA) programming model. To evaluate the performance of the proposed approach, an ASUS Xtion 3D camera, laptop, and NVIDIA TX2 are employed to conduct extensive experiments. The experimental results show that compared with the traditional VO algorithm, the proposed approach gives better results over the traditional VO algorithm.

AB - An enhanced visual odometry (VO) system is proposed to improve the accuracy of pose estimation based on a corrected model, and the matching algorithm is implemented on graphical processing units (GPUs) so that the computation can be accelerated in parallel and in real-time using the compute unified device architecture (CUDA) programming model. To evaluate the performance of the proposed approach, an ASUS Xtion 3D camera, laptop, and NVIDIA TX2 are employed to conduct extensive experiments. The experimental results show that compared with the traditional VO algorithm, the proposed approach gives better results over the traditional VO algorithm.

KW - CUDA

KW - GPU

KW - Visual odometry

UR - http://www.scopus.com/inward/record.url?scp=85060315763&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060315763&partnerID=8YFLogxK

U2 - 10.1109/GCCE.2018.8574869

DO - 10.1109/GCCE.2018.8574869

M3 - Conference contribution

AN - SCOPUS:85060315763

T3 - 2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018

SP - 55

EP - 56

BT - 2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -