A Bayesian Approach to Object Detection Using Probabilistic Appearance-Based Models

Rozenn Dahyot, Pierre Charbonnier, Fabrice Heitz

[pdf] - Copyright (c) Springer-Verlag

In this paper, we introduce a Bayesian approach, inspired by Probabilistic Principal Component Analysis, to detect objects in complex scenes using appearance based models. The originality of the proposed framework is to explicitly take into account general forms of the underlying distributions, both for the in-eigenspace distribution and for the observation model. The approach combines linear data reduction techniques to preserve computational efficiency, non-linear constraints on the in-eigenspace distribution to model complex variabilities and non-linear robust observation models to cope with clutter, outliers and occlusions. The resulting statistical representation generalizes most existing PCA-based models and leads to the definition of a new family of non-linear probabilistic detectors. The performance of the approach is assessed using ROC (Receiver Operating Characteristic) analysis on several representative data-bases, showing a major improvement in detection performances with respect to the standard methods that have been the references up to now.