Abstract
Many works address the problem of ob ject detection by means of machine learning with boosted classifiers. They exploit slid- ing window search, spanning the whole image: the patches, at all possi- ble 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 statistical- based search approach for ob ject 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 tempo- ral coherency of the pedestrians. Several tests on both still images and videos on common datasets are provided in order to demonstrate the relevant 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.