Computer Vision
Enabling computers and devices to understand what they see.
Project
Projector-Whiteboard-Camera System for Remote Collaboration
Visual Echo Cancellation for Seamless Integration of Remote Sites About In a typical remote collaboration setup, two or more projector-camera pairs are “cross-wired” to form a full-duplex system for two-way communication. A whiteboard can be…
Publication
High resolution multispectral image capture
Project
Speaker Verification: Text-Dependent vs. Text-Independent
Speaker verification is the process of verifying the claimed identity of a speaker based on the speech signal from the speaker (voiceprint). There are two types of speaker verification systems: Text-Independent Speaker Verification (TI-SV) and…
Project
Microphone Array Audio Spatialization
Enhancing Stereophonic Conferencing with Microphone Arrays Through Sound Field Warping and Audio Spatialization Audio samples mono.wma: Traditional mono output from a microphone array. speaker.wma: Array audio spatialized over a pair of loudspeakers. headphone.wma: Array audio…
Project
Audio Spatialization and Multichannel Acoustic Echo Cancellation (AEC)
About the System In multiparty conferencing, one hears voices of more than one remote participants. Current commercial systems mix them into a single mono audio stream, and thus all voices of remote participants will sound…
Project
Human Action and Activity Recognition
Expandable Data-Driven Graphical Modeling of Human Actions Based on Salient Postures. This paper presents a graphical model for learning and recognizing human actions. Specifically, we propose to encode actions in a weighted directed graph, referred…
Project
VisualScreen
Transforming an ordinary screen into a Touch Screen with a camera. About Touch screens are very convenient because one can directly point to where it is interesting. This paper presents an inexpensive technique to transform…
Project
VisualPanel
Transforming an ordinary paper into a wireless mobile input device. Virtual mouse, keyboard and 3D controller with an ordinary piece of paper. Abstract In many intelligent environments, instead of using conventional mice, keyboards and joysticks,…
Project
Re-rendering from a Sparse Set of Images
We present a framework for view-dependent rendering from arbitrary viewpoints and relighting under novel illumination conditions of a real object from a sparse set of images and a pre-acquired geometric model of the object. Using…
Project
Eye-Gaze Correction for Video Telecommunications
The lack of eye contact in desktop video teleconferencing substantially reduces the effectiveness of video contents. While expensive and bulky hardware is available on the market to correct eye gaze, researchers have been trying to…