About AMP Lab        Projects        Downloads        Publications        People        Links

Group Member

Yao-Jen Chang
Research Scientist

Personal Homepage:  http://www.andrew.cmu.edu/~yaojen
Email: kevinchang at cmu.edu

Office: Porter Hall B23
Lab: Porter Hall B6
Phone: 412-268-4464
Fax: 412-268-3890
Mailing Address:
Department of ECE, Carnegie Mellon University,
5000 Forbes Avenue, Pittsburgh,
PA 15213-3890

[Research Interests]        [Project]      [Publications

Research Interests

Research Focus:

Design mobile robots for active capturing and rendering of environments. 

Investigate distributed video surveillance networks based on miniaturized smart cameras capable of performing on-board visual analysis and video streaming. 

Investigate a video surveillance architecture and framework for rapid development of video surveillance applications for home care, home security, and parking lot services.

Investigate a user adaptation method for creation of image-based speech animation of a novel person with limited video corpus.

Develop a biometrics-based cryptographic key generation mechanism for generating cryptographic keys on resource-constrained handheld devices.

  Top of this page

 

Projects
Active Image-based Rendering with Robot-based Imaging Testbed

The Robot-based Imaging Test-bed (RIT) is an open source toolkit designed to be used with a network of wireless robots with imaging cameras. The toolkit will provide the infrastructure for wireless networking, overhead camera localization, path planning, path following and image processing. Developers can install various high level applications to use the base classes provided by the toolkit for test purposes. The focus is to construct a robust and well documented system that is easy to manipulate and expand upon while providing a wide range of image processing and distributed robotics capability.

Please refer to the Robot-based Imaging Test-bed page for more information. 

 

Software Development Toolkit for Video Surveillance

As computers become more powerful, they facilitate the possibility of more sophisticated and more powerful tracking algorithms. The knowledge gap between the novice and the expert continues to widen. Even for experts, there can be a significant time cost to instantiate an algorithm - even if it is for comparison purposes only. Enter ICTrack. Our goal is two fold. For the novice, we create a flexible interface that the novice can use to manipulate advanced algorithms without having to know the sometimes pedantic details. For the expert, we provide a framework for developing new algorithms and testing them verus existing techniques.

Please refer to the ICTrack project page for more information. 

 

Algorithms for Key Generation based on Biometrics 

Instead of using PINs and passwords as cryptographic keys that are either easy to forget or vulnerable to dictionary attacks, easy-to-carry and difficult-to-transfer keys can be generated based on user-specific biometric information. In this paper, a framework is proposed to generate stable cryptographic keys from biometric data that is unstable in nature. The proposed framework differs from prior work in that user-dependent transforms are utilized to generate more compact and distinguishable features. Thereby, a longer and more stable bitstream can be generated as the cryptographic key.

Please refer to the Key generation based on biometrics project page for more information. 

 

Top of this page

 

Publications

Journal Papers:

Conference Papers: 

Patents: 

Top of this page


This website is maintained by Devi Parikh
Copyright © 2001 
Advanced Multimedia Processing Lab. All rights reserved.
Revised: January 18, 2008