Looking at People Using Partial Least Squares

Abstract

Analysis of images involving humans is of significant interest in computer vision because problems such as detection, modeling, recognition, and tracking are fundamental to model interactions between people and understand high-level activities. Visual information contained in images is generally represented using descriptors (features). Many general classes of descriptors have been proposed focusing on different characteristics of images. Therefore, if one considers only a single descriptor, one might ignore useful information for a given task, compromising performance. In this research we consider a rich set of image descriptors analyzed by a statistical technique known as Partial Least Squares (PLS). PLS is a class of methods for modeling relations between sets of observations by means of latent variables and it is used to project exemplars from a very high dimensional feature space onto a low dimensional subspace.

We demonstrate the effectiveness of combining a richer set of descriptors using PLS in two significant tasks in computer vision. First, we propose a method to detect humans, which is then extended to handle partial occlusion and finally a framework based on PLS regression models is incorporated to further reduce the computational cost. Second, an object recognition framework based on a one-against-all scheme is exploited for appearance-based person modeling and face identification.