Reduced Search Space for Rapid Bicycle Detection

M. Nilsson, H. Ardö, A. Laureshyn, A. Persson

2013

Abstract

This paper describes a solution to the application of rapid detection of bicycles in low resolution video. In particular, the application addressed is from video recorded in a live environment. The future aim from the results in this paper is to investigate a full year of video data. Hence, processing speed is of great concern. The proposed solution involves the use of an object detector and a search space reduction method based on prior knowledge regarding the application at hand. The method using prior knowledge utilizes random sample consensus, and additional statistical analysis on detection outputs, in order to define a reduced search space. It is experimentally shown that, in the application addressed, it is possible to reduce the full search space by 62% with the proposed methodology. This approach, which employs a full detector in combination with the design of a simple and fast model that can capture prior knowledge for a specific application, leads to a reduced search space and thereby a significantly improved processing speed.

Paper Citation

in Harvard Style

Nilsson M., Ardö H., Laureshyn A. and Persson A. (2013). Reduced Search Space for Rapid Bicycle Detection . In Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-8565-41-9, pages 453-458. DOI: 10.5220/0004264804530458

in Bibtex Style

@conference{icpram13,
author={M. Nilsson and H. Ardö and A. Laureshyn and A. Persson},
title={Reduced Search Space for Rapid Bicycle Detection},
booktitle={Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2013},
pages={453-458},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004264804530458},
isbn={978-989-8565-41-9},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Reduced Search Space for Rapid Bicycle Detection
SN - 978-989-8565-41-9
AU - Nilsson M.
AU - Ardö H.
AU - Laureshyn A.
AU - Persson A.
PY - 2013
SP - 453
EP - 458
DO - 10.5220/0004264804530458