VINet: Visual-Inertial Odometry as a Sequence-to-Sequence Learning Problem

@inproceedings{Clark2017VINetVO,
  title={VINet: Visual-Inertial Odometry as a Sequence-to-Sequence Learning Problem},
  author={Ronald Clark and Sen Wang and Hongkai Wen and Andrew Markham and Agathoniki Trigoni},
  booktitle={AAAI},
  year={2017}
}
In this paper we present an on-manifold sequence-tosequence learning approach to motion estimation using visual and inertial sensors. It is to the best of our knowledge the first end-to-end trainable method for visual-inertial odometry which performs fusion of the data at an intermediate feature-representation level. Our method has numerous advantages over traditional approaches. Specifically, it eliminates the need for tedious manual synchronization of the camera and IMU as well as eliminating… CONTINUE READING
Tweets
This paper has been referenced on Twitter 63 times. VIEW TWEETS

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 51 CITATIONS, ESTIMATED 39% COVERAGE

FILTER CITATIONS BY YEAR

2017
2019

CITATION STATISTICS

  • 5 Highly Influenced Citations

  • Averaged 23 Citations per year over the last 3 years

  • 35% Increase in citations per year in 2018 over 2017

References

Publications referenced by this paper.
SHOWING 1-10 OF 24 REFERENCES

Similar Papers

Loading similar papers…