A macrofeature layout selection is proposed for object detection. Macrofeatures [2] are mid-
level features that jointly encode a set of low-level features in a neighborhood. Our method …

In real-world surveillance systems, where variation of light and camera parameters can
sometimes severely impair the normal operation of background subtraction algorithms …

We present a new X-ray analysis mainly based on ROSAT HRI data. The HRI spatial
resolution combined with an improved wavelet analysis method and with complementary …

We examine a set of biologically inspired features and apply it to the multiclass object
recognition problem. To obtain these features we modify HMAX, which is based on a …

Described is a system for visual activity recognition. In operation, the system detects a set of
objects of interest (OI) in video data and determines an object classification for each object …

In the field of visual attention, bottom-up or saliency-based visual attention allows primates
to detect non-specific conspicuous objects or targets in cluttered scenes. Simple multi-scale" …

In the lab, I spent countless hours working on the vehicles and preparing field experiments
and demonstrations. Laurent Bouraoui and Armand Yvet were by my side and provided me …

Macrofeatures are mid-level features that jointly encode a set of low-level features in a
neighborhood. We propose a macrofeature layout selection technique to improve …

A key to solving the multiclass object recognition problem is to extract a set of features which
accurately and uniquely capture the salient characteristics of different objects. In this work …

A key to solving the multiclass object recognition problem is to extract a set of features which
accurately and uniquely capture the salient characteristics of different objects. We show that …