Object recognition in natural surroundings is one of the most ambitious goals of digital image processing. In our work, strategies for the analysis of traffic scenes are investigated. The Hierarchical Structure Code (HSC) is applied to this problem and it has been shown that fast object recognition is possible. The HSC provides a unified approach for contour-based and region-based descriptions ...

PDBlib is an extensible object oriented class library written in C++ for representing the 3-dimensional structure of biological macromolecules. PDBlib forms the kernel of a larger software framework being developed for assiting in knowledge discovery from macromolecular structure data. The software design strategy used by PDBlib, how the library may be used and several prototype applications th...

The classical problem of tracking the location of mobile objects in a wireless sensor network is one that has drawn considerable attention from the sensor network research community for quite a long time, as this problem provides an abstraction for many applications that can be built over wireless sensor networks. However, many technical issues still exist in this field. In order to provide a b...

We built a prototype tool for browsing constraint systems for the layout of graphical objects. It has two views: In one view, the tool visualizes a constraint system as a threedimensional graph structure, which shows the overall structure of the constraint system. The viewer can change the layout to focus on the part of constraints. The other view shows the target diagram. It also animates the ...

Assuming a first-order auto-regressive model for the auto-correlation structure between observations, in this paper, a transformation method is first employed to eliminate the effect of auto-correlation. Then, a maximum likelihood estimator (MLE) of a step change in the parameters of the transformed model is derived and three separate EWMA control charts are used to monitor the parameters of th...

1. Introduction Any theory of how language is internally organized and how it interacts with other mental capacities must address the fundamental question of how syntactic and lexico-semantic information interact at one central linguistic compositional level, the sentence level. With this general objective in mind, we examine “ " light-verbs” " , so called because the main thrust of the semanti...

Our main focus is the registration and visualization of a pre-built 3D model from preoperative images to the camera view of a minimally invasive surgery (MIS). Accurate estimation of soft-tissue deformations is key to the success of such a registration. This paper proposes an explicit statistical model to represent global non-rigid deformations. The deformation model built from a reference obje...

In this paper, I will provide an overview of our project on 3D object and face modeling from images taken by a free-moving camera. We strive to advance the state of the art in 3D computer vision, and develop flexible and robust techniques for ordinary users to gain 3D experience from a set of casually collected 2D images. Applications include product advertisement on the Web, virtual conference...

In this paper, we present a multi-formalism modeling framework (abbreviated by MFMF) for modeling and simulation. The proposed framework is defined based on the concepts of meta-models and uses object-orientation to overcome the complexities and to enhance the extensibility. The framework can be used as a basis for modeling by various formalisms and to support model composition in a unified man...