Detection and Orientation Estimation for Cyclists by Max Pooled Features

Wei Tian, Martin Lauer

2017

Abstract

In this work we propose a new kind of HOG feature which is built by the max pooling operation over spatial bins and orientation channels in multilevel and can efficiently deal with deformation of objects in images. We demonstrate its invariance against both translation and rotation in feature levels. Experimental results show a great precision gain on detection and orientation estimation for cyclists by applying this new feature on classical cascaded detection frameworks. In combination of the geometric constraint, we also show that our system can achieve a real time performance for simultaneous cyclist detection and its orientation estimation.

Paper Citation

in Harvard Style

Tian W. and Lauer M. (2017). Detection and Orientation Estimation for Cyclists by Max Pooled Features . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-226-4, pages 17-26. DOI: 10.5220/0006085500170026

in Bibtex Style

@conference{visapp17,
author={Wei Tian and Martin Lauer},
title={Detection and Orientation Estimation for Cyclists by Max Pooled Features},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={17-26},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006085500170026},
isbn={978-989-758-226-4},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017)
TI - Detection and Orientation Estimation for Cyclists by Max Pooled Features
SN - 978-989-758-226-4
AU - Tian W.
AU - Lauer M.
PY - 2017
SP - 17
EP - 26
DO - 10.5220/0006085500170026