REBoost: Probabilistic resampling for boosted pedestrian detection

Lai, Shiming, Zhang, Maojun, Liu, Yu and Theobald, Barry-John (2011) REBoost: Probabilistic resampling for boosted pedestrian detection. Optical Engineering (OE), 50 (12). ISSN 1560-2303

Full text not available from this repository.


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.

Item Type: Article
Faculty \ School: Faculty of Science > School of Computing Sciences
UEA Research Groups: Faculty of Science > Research Groups > Interactive Graphics and Audio
Depositing User: Users 2731 not found.
Date Deposited: 23 Feb 2012 22:21
Last Modified: 13 Jan 2024 01:20
DOI: 10.1117/1.3658762

Actions (login required)

View Item View Item