Honours projects 2010

Projects supervised by Vera Chung

VC 1: Multimedia Information Retrieval for web application
With the rapid increasing use of multimedia data such as audio, image and video, there is a strong demand for efficient techniques for their storage, browsing, indexing, and retrieval to exploit the full benefit of the explosive growth and application of multimedia data. This project will study and design some techniques for the application of digital museum, entertainment, internet shopping, and medical image retrieval system.

Requirement: Java or C/C++ programming language

VC 2: Digitizing Personal Experiences: Capture and Retrieval of Life Log
In wearable computing environments, digitization of personal experiences will be made possible by continuous recordings using a wearable video camera. This could lead to the “automatic life-log application”. This project will develop a “context-based video retrieval system for life-log applications”. The life log system will captures video, audio, acceleration sensor, gyro, GPS, annotations, documents, web pages, and emails, and provides functions that make efficient video browsing and retrieval possible by using data from these sensors, some databases and various document data.

Requirement: Java or C/C++ programming language

VC 3: Context-based Video Retrieval System for the Life-Log Applications
The custom of writing a diary is common all over the world. This fact shows that many people like to log their everyday lives. However, to write a complete diary, a person must recollect and note what was experienced without missing anything. For an ordinary person, this is impossible. It would be nice to have a secretary who observed your everyday life and wrote your diary for your. In the future, a wearable computer may become such a secretary-agent. This project will study and develop a “life-log agent logs our everyday life on storage devices instead of paper, using multimedia such as small camera instead of a pencil.

Requirement: Java or C/C++ programming language

NICTA 1: Automatic Cognitive Load Measurement via Multimodalities
USyd Supervisor: Dr. Vera Chung (v.chung@usyd.edu.au)
NICTA Supervisor: Dr. Eric Choi (eric.choi@nicta.com.au)

Cognitive load is variously described as the level of perceived mental effort associated with thinking and reasoning in a human. Tasks performed under stressful conditions, or requiring complex hand/eye coordination can markedly increase cognitive load, and thus potentially interfere with other thought processes and consequently reduce overall task performance. If a user’s existing level of cognitive load can be assessed in real time, an intelligent system could potentially adapt its behaviours to implement strategies that reduce the cognitive load and correspondingly increase the task performance. While the concept of cognitive load itself may be more a theoretical construct, its measurement can lead to numerous real-world applications, e.g. in call centres for gathering customer emotional intelligence, and in electronic gaming for tailoring the plots according to a gamer’s cognitive and emotional states.

We have been researching a non-intrusive and online method for measuring cognitive load by analysing multimodal interaction behaviours of humans, including speech, gestures and physiological signals, for various types of tasks. This project aims to design and implement a new set of software tools which can be used to analyse the multimodal data and automatically classify their cognitive load levels. Initial effort will be required to identify and annotate segments of the various streams of modality data that are temporally related. Later stage of the project will involve building automatic cognitive load classifiers based on the Orange Machine Learning tools.

Student Requirements: Software development and programming skills required (Java/C/C++). Good knowledge in statistical methods and signal processing highly desired.