NONPLANARITY AND EFFICIENT MULTIPLE FEATURE EXTRACTION

Ernst D. Dickmanns, Hans-Joachim Wuensche

2006

Abstract

A stripe-based image evaluation scheme for real-time vision has been developed allowing efficient detection of the following classes of features: 1. ‘Nonplanarity’ feature for separating image regions treatable by planar shading models from the rest containing textured regions and corners; 2. edges and 3. smoothly shaded regions between edges, and 4. corners for stable 2-D feature tracking. All these features are detected by evaluating receptive fields (masks) with four mask elements shifted through stripes, both in row and column direction. Efficiency stems from re-use of intermediate results in mask elements in neighboring stripes and from coordinated use of these results in different feature extractors. Corner detection with compute-intensive algorithms can be confined to a small (but highly likely) fraction of the images exploiting the efficient nonplanarity feature. Application to road scenes is discussed.

Paper Citation

in Harvard Style

D. Dickmanns E. and Wuensche H. (2006). NONPLANARITY AND EFFICIENT MULTIPLE FEATURE EXTRACTION . In Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, ISBN 972-8865-40-6, pages 198-205. DOI: 10.5220/0001370701980205

in Bibtex Style

@conference{visapp06,
author={Ernst D. Dickmanns and Hans-Joachim Wuensche},
title={NONPLANARITY AND EFFICIENT MULTIPLE FEATURE EXTRACTION},
booktitle={Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP,},
year={2006},
pages={198-205},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001370701980205},
isbn={972-8865-40-6},
}

in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP,
TI - NONPLANARITY AND EFFICIENT MULTIPLE FEATURE EXTRACTION
SN - 972-8865-40-6
AU - D. Dickmanns E.
AU - Wuensche H.
PY - 2006
SP - 198
EP - 205
DO - 10.5220/0001370701980205