Many works address the problem of object detection by means of machine learning with boosted classifiers. They exploit sliding window search, spanning the whole image: the patches, at all possible positions and sizes, are sent to the classifier. Several methods have been proposed to speed up the search (adding complementary features or using specialized hardware). In this paper we propose a statisticalbased search approach for object detection which uses a Monte Carlo sampling approach for estimating the likelihood density function with Gaussian kernels. The estimation relies on a multi-stage strategy where the proposal distribution is progressively refined by taking into account the feedback of the classifier (i.e. its response). For videos, this approach is plugged in a Bayesian-recursive framework which exploits the temporal coherency of the pedestrians. Several tests on both still images and videos on common datasets are provided in order to demonstrate therelevant speedup and the increased localization accuracy with respect to sliding window strategy using a pedestrian classifier based on covariance descriptors and a cascade of Logitboost classifiers.

Multi-stage Sampling with Boosting Cascades for Pedestrian Detection in Images and Videos / Gualdi, Giovanni; Prati, Andrea; Cucchiara, Rita. - ELETTRONICO. - 6316:6(2010), pp. 196-209. (Intervento presentato al convegno 11th European Conference on Computer Vision, ECCV 2010 tenutosi a Heraklion, Crete, grc nel 5-11 September 2010) [10.1007/978-3-642-15567-3_15].

Multi-stage Sampling with Boosting Cascades for Pedestrian Detection in Images and Videos

GUALDI, Giovanni;PRATI, Andrea;CUCCHIARA, Rita
2010

Abstract

Many works address the problem of object detection by means of machine learning with boosted classifiers. They exploit sliding window search, spanning the whole image: the patches, at all possible positions and sizes, are sent to the classifier. Several methods have been proposed to speed up the search (adding complementary features or using specialized hardware). In this paper we propose a statisticalbased search approach for object detection which uses a Monte Carlo sampling approach for estimating the likelihood density function with Gaussian kernels. The estimation relies on a multi-stage strategy where the proposal distribution is progressively refined by taking into account the feedback of the classifier (i.e. its response). For videos, this approach is plugged in a Bayesian-recursive framework which exploits the temporal coherency of the pedestrians. Several tests on both still images and videos on common datasets are provided in order to demonstrate therelevant speedup and the increased localization accuracy with respect to sliding window strategy using a pedestrian classifier based on covariance descriptors and a cascade of Logitboost classifiers.
2010
11th European Conference on Computer Vision, ECCV 2010
Heraklion, Crete, grc
5-11 September 2010
6316
196
209
Gualdi, Giovanni; Prati, Andrea; Cucchiara, Rita
Multi-stage Sampling with Boosting Cascades for Pedestrian Detection in Images and Videos / Gualdi, Giovanni; Prati, Andrea; Cucchiara, Rita. - ELETTRONICO. - 6316:6(2010), pp. 196-209. (Intervento presentato al convegno 11th European Conference on Computer Vision, ECCV 2010 tenutosi a Heraklion, Crete, grc nel 5-11 September 2010) [10.1007/978-3-642-15567-3_15].
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/643489
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 24
  • ???jsp.display-item.citation.isi??? 16
social impact