Honours Projects 2010

Projects supervised by Jian Zhang (NICTA), Zhiyong Wang and David Feng

Multimedia Search and Mining
Recent multimedia information technologies (in terms of content analysis and management, and content representation) have rapidly developed and begun to move towards commercialization in some specific applications. Advances in image/video processing, computer vision, artificial intelligence and database technologies have been the major enablers for this phenomenon. While explosion of multimedia data brings us new challenges to multimedia content understanding, organization, presentation and search especially in terms of scalability. Both computational costs and performance are still far from satisfactory with the increase of multimedia data and the increase of semantic demands. While on the other hand, these increasing data as well as the massive grassroots users also provides us new opportunities to attack these challenges as well as conventional problems in multimedia analysis and computer vision. In this project, we will focus on fast advanced search for image and video contents, which sustainably contributes to the image/video retrieval. High level content description and representation of image and video is a direction of content analysis and management research, however it still remains a challenge today, and hence attracts the interest of this research group. It is possible to extend this project for a postgraduate research project at PhD level.

Objects Classification and Event Detection in Surveillance Video
Object classification is a further step to object detection and tracking in understanding of video. Without object classification, we can only know something is moving in the video sequences, but don’t know what it is. With the information from object tracking and classification, it may become possible to understand the activities and events happening in the video sequences. The task of this project is to investigate the existing object classification technologies and develop one for categorizing moving vehicles or human detected from the surveillance videos. This is a challenging, but also exciting project. You have access understate the state-of-art video processing tools and facilitates. The knowledge you learned from the courses of computer vision, neural network, pattern recognition and machine learning can all find their utilization in this project. Your programming skills will also be developed as you will develop a demo in software. It is possible to extend this project for a postgraduate research project at PhD level.