Using Inertial Data to Enhance Image Segmentation - Knowing Camera Orientation Can Improve Segmentation of Outdoor Scenes

Osian Haines, David Bull, J. F. Burn

2015

Abstract

In the context of semantic image segmentation, we show that knowledge of world-centric camera orientation (from an inertial sensor) can be used to improve classification accuracy. This works because certain structural classes (such as the ground) tend to appear in certain positions relative to the viewer. We show that orientation information is useful in conjunction with typical image-based features, and that fusing the two results in substantially better classification accuracy than either alone – we observed an increase from 61% to 71% classification accuracy, over the six classes in our test set, when orientation information was added. The method is applied to segmentation using both points and lines, and we also show that combining points with lines further improves accuracy. This work is done towards our intended goal of visually guided locomotion for either an autonomous robot or human.

Paper Citation

in Harvard Style

Haines O., Bull D. and Burn J. (2015). Using Inertial Data to Enhance Image Segmentation - Knowing Camera Orientation Can Improve Segmentation of Outdoor Scenes . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-090-1, pages 21-32. DOI: 10.5220/0005274000210032

in Bibtex Style

@conference{visapp15,
author={Osian Haines and David Bull and J. F. Burn},
title={Using Inertial Data to Enhance Image Segmentation - Knowing Camera Orientation Can Improve Segmentation of Outdoor Scenes},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={21-32},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005274000210032},
isbn={978-989-758-090-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)
TI - Using Inertial Data to Enhance Image Segmentation - Knowing Camera Orientation Can Improve Segmentation of Outdoor Scenes
SN - 978-989-758-090-1
AU - Haines O.
AU - Bull D.
AU - Burn J.
PY - 2015
SP - 21
EP - 32
DO - 10.5220/0005274000210032