Information & computer science publications
-
VideoQuest: Managing Large-Scale Aerial Video Database Through Automated Content Extraction
In this paper, we introduce an aerial video management and exploitation system named VideoQuest that manages large-scale aerial video database through automated video processing and content extraction.
-
Collaborative Effects of Mobile Sensor Network Localization through Distributed Fusion of Multi-Modal Navigations
This paper addresses the problem of localizing both absolute and relative 3-D positions of mobile sensor network nodes by fusing inertial measurements and radio frequency (RF) ranging measurements.
-
Color Enhancement in Image Fusion
We propose an innovative approach to enhance the color in image fusion. We propose a gamma correction function to the normalized color components.
-
Multimedia Information Extraction Roadmap
-
Runtime Certification
We outline a suitable framework, in which the basis for certification is changed from compliance with standards to the construction of explicit goals, evidence, and arguments (generally called an “assurance…
-
A Semantic Web Reasoner for Rules, Equations and Constraints
We describe a reasoner for OWL ontologies and SWRL policies used on cognitive radios to control dynamic spectrum access.
-
Visual Odometry System Using Multiple Stereo Cameras and Inertial Measurement Unit
In this paper, we present a robust method that addresses these challenges using a human wearable system with two pairs of backward and forward looking stereo cameras together with an…
-
Precise Visual Navigation Using Multi-Stereo Vision and Landmark Matching
In this paper, we propose a set of techniques which greatly reduce the long term drift and also improve its robustness to many failure conditions.
-
On-The-Move Independently Moving Target Detection
This paper describes a system for automatically detecting potential targets (that pop-up or move into view) and to cue the operator to potential threats. We present a 3D approach for…
-
Preceding Vehicle Trajectory Prediction by Multi-Cue Integration
In this paper we describe an approach to detect and predict the driving trajectory of a preceding vehicle on highway. In particular, we focus on detecting and predicting the changing…
-
Reduced Resolution Residual Coding for H.264-Based Compression System
This paper describes a macroblock-based mixed resolution video encoding system. By reducing the spatial resolution of some macroblock residuals intelligently, our preliminary experiments show up to 20% improvement in video…
-
The Use of Word N-grams and Parts of Speech for Hierarchical Cluster Language Modeling
We present extensions to the work of backoff hierarchical class n-gram language modeling of Zitouni et al. (2003) by studying the efficacy of exploring the use of parts of speech…