REBoost: probabilistic resampling for boosted pedestrian detection

Shiming Lai; Maojun Zhang; Yu Liu; Barry-John Theobald

doi:10.1117/1.3658762

1 December 2011 REBoost: probabilistic resampling for boosted pedestrian detection

Shiming Lai, Maojun Zhang, Yu Liu, Barry-John Theobald

Author Affiliations +

Optical Engineering, Vol. 50, Issue 12, 127203 (December 2011). https://doi.org/10.1117/1.3658762

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.

©(2011) Society of Photo-Optical Instrumentation Engineers (SPIE)

Citation Download Citation

Shiming Lai, Maojun Zhang, Yu Liu, and Barry-John Theobald "REBoost: probabilistic resampling for boosted pedestrian detection," Optical Engineering 50(12), 127203 (1 December 2011). https://doi.org/10.1117/1.3658762

Published: 1 December 2011

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available