Tools
ToolsLai, 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.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.
| 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 |
| URI: | https://ueaeprints.uea.ac.uk/id/eprint/37449 |
| DOI: | 10.1117/1.3658762 |
Actions (login required)
 |
View Item |