Estimating motion in scenes containing multiple moving objects remains a diicult problem in computer vision yet is solved eeortlessly by humans. In this thesis we present a computational investigation of this astonishing performance in human vision. The method we use throughout is to formulate a small number of assumptions and see the extent to which the optimal interpretation given these assum...

The key to high performance in image sequence coding lies in an efficient reduction of the temporal redundancies. For this purpose, motion estimation and compensation techniques have been suc­ cessfully applied. This paper studies motion estimation algorithms in the context of first generation coding techniques commonly used in digital TV. In this framework, estimating the motion in the scene i...

This paper unifies “line-process” approaches for regularization with discontinuities and robust estimation techniques. We generalize the notion of a “line process” to that of an analog “outlier process” and show that a problem formulated in terms of outlier processes can be viewed an terms of robust statistics. We also characterize a class of robust statistical problems for which an equivalent ...

We propose an approach to 3D facial pose estimation that, unlike most state-of-the-art techniques, can handle arbitrary poses, including extreme out-of-plane rotations, background clutter and facial expressions. It relies on a large database of registered face images of different people viewed from several perspectives. We use a powerful image retrieval technique to match the input image agains...

This paper investigates the validity of LR estimation for long-term F0 using Aitkin (1995)’s formula. Although this formula has been developed to estimate the LR of reflective index of glass fragments, previous studies such as Kinoshita (2001) and Rose, Osanai, and Kinoshita (2003) have shown that Aitkin’s formula can be applied to speech data. The experiments in this study revealed, however, t...

In this paper, we propose a novel approach to perform efficient motion estimation specific to surveillance videos. A real-time background subtractor is used to detect the presence of any motion activity in the sequence. Two approaches for selective motion estimation, GOP-by-GOP and Frame-byFrame, are implemented. In the former, motion estimation is performed for the whole group of pictures (GOP...

In a number of practical scenarios, such as video conferencing and visual human/computer interaction, objects that belong to a well defined class are segmented, normalized, and encoded, after which they are stored and/or transmitted, and subsequently reconstructed. The Karhunen-Loève Transform (KLT) optimally concentrates the signal power in a relatively small number of uncorrelated coefficient...