Share Email Print

Optical Engineering

REBoost: probabilistic resampling for boosted pedestrian detection
Author(s): Shiming Lai; Maojun Zhang; Yu Liu; Barry-John Theobald
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

Cascaded object detectors have demonstrated great success in fast object detection, where image regions can quickly be rejected using a cascade of increasingly complex rejectors/detectors. Although such cascaded detectors typically are fast and require minimal computation, they usually require iterative training, where classifiers are retrained to optimize rejection thresholds after testing on a validation set. We propose a cascaded object detector that uses probabilistic resampling for boosting reweighting, which has the advantage that only a single training step is required. Decision thresholds can be tuned on a validation set without the need for classifier retraining. Empirical results on a pedestrian detection task demonstrate that this reweighting results in a strong classifier that quickly rejects image regions and offers higher accuracy than other competing approaches.

Paper Details

Date Published: 1 December 2011
PDF: 8 pages
Opt. Eng. 50(12) 127203 doi: 10.1117/1.3658762
Published in: Optical Engineering Volume 50, Issue 12
Show Author Affiliations
Shiming Lai, National Univ. of Defense Technology (China)
Maojun Zhang, National Univ. of Defense Technology (China)
Yu Liu, National Univ. of Defense Technology (China)
Barry-John Theobald, Univ. of East Anglia Norwich (United Kingdom)

© SPIE. Terms of Use
Back to Top