Undergraduate Scholarships

A few projects in computer vision are offered this year.  Some of of them may be jointly supervised with staff members of the School.  If you have in mind a computer vision research topic that is not listed below, I would be interested to hear from you.  Please note that I can only supervise up to 3 projects in any one year.

With appropriate adjustment, any of the projects below could be suitable for a BE(SE) final year project (12 points), an Honours Research Project (24 points), or a MSc project (24 points).

Experience has shown that it can be very beneficial for research students to have a group of people with related interests to share ideas with. A student undertaking any of the projects below is expected to join the Computer Vision Research Group and will be expected to attend and contribute to group meetings and discussions. Such a student will be housed in the Computer Vision Research Group Laboratory in Room 2.09 of the Computer Science building. You are also strongly advised to take the CITS4240 Computer Vision unit offered in the first semester.

My past final-year project students:

• Tyson STOLARSKI (2010, CEED project, Mechatronics Engineering), "Implementation of an Augmented Reality Visualisation System for Industrial Automation"
• Calin BORCEAU (2010, Mechatronics Engineering), "An Extensible Platform for Real-Time Monocular SLAM"
• Evgeni SERGEEV (2009, Honours), "Tracking Boundaries in Video via Segmentation"
• Michael GOOLD (2009, Mechantronics Engineering), "Recognising Guitar Chords in Real-Time"
• Barry VAN OUDTSHOORN (2008, Honours), "Investigating the Feasibility of Near Real-Time Music Transcription on Mobile Devices" (WAITTA finalist)
  
• Lih Wern HIEW (2007, Mechatronics Engineering), "Adaptive background modelling for motion tracking"
• Eko Kumiawan TENGGARA (2007, Honours), "Human Head Tracking in Cluttered Scenes"
• Daniel DELUCA-CARDILLO (2006, Honours), "3D Pose Recovery for the Human Arm" (WAITTA finalist)
• Robert BUDIMAN (2005, Honours), "Implementing motion capture for 3D cartoon movies"
• Chi Chiu CHENG (2003, MSc), "Scanner Video Mosaicing"
• John DARRINGTON (2002, Honours), "Character recognition using a multilayer perceptron classifier and orthogonal moments on the unit disc" (at Murdoch University)

1. Markerless motion capture and computer Animation.
   This project is perhaps the most challenging project in the list here. The aim of the project is to track the movement of a 3D skeleton model of a human subject from video sequences. The recovered movement can be applied in a wide range of applications, such as computer animation, rehabilitation and sports injury analysis. The project will require the student to have a very good mathematics background (Monte Carlo Sampling and basic statistics) and knowledge in computer vision and image processing. Students who don't have any background in computer vision must take the CITS4240 (Computer Vision) unit in the first semester.
   The scope of the project will be trimmed so that it can be completed within one year. If you are interested, please contact me for further details of the project.
   Note: this project was taken in 2006 by Mr. Daniel Deluca-Cardillo, of whom I was the sole supervisor. The project for this year will be an extension of Daniel's implementation. A copy of Daniel's thesis can be made available to interested students.
   

2. Visual tracking of human heads in video
   The aim of this project is to study, analyze, and evaluate a couple of visual tracking techniques, including the conventional particle filter and the unscented particle filter. The implementation part of the project will involve applying these two filters on the tracking of human heads in video sequences. Similar (but less difficult) to the markerless motion capture project above, the project will require a good knowledge in mathematics, in particular, statistics. It is also important that the unit CITS4240 (Computer Vision) is taken in the first semester.
   Note: this project was taken by Mr. Eko Tenggara.
   
   
3. Adaptive Background/Foreground Segmentation.
   This project studies the segmentation of foreground objects (e.g. people) in a dynamic, textured background from video sequences.  Examples of such time-varying texture backgrounds include changing illumination, swaying trees, waves on water, moving clouds, etc.
   Background/foreground segmentation has  extensive applications in movie editing, video surveillance, and image synthesis.  In movie editing, the images of the human actors are often required to be segmented from the background and then superimposed into different scenes; in video surveillance of a scene (e.g. train stations, indoor laboratories) over a long period of time, segmentation of the interesting objects, such as people and vehicles from a background under variable lighting conditions is often required; in image synthesis, moving objects often arise as outliers and their segmentation from the image sequences needs to be integrated with the estimation of camera geometry.
   References:
   [1] C. Stauffer and W. E. L. Grimson, "Adaptive background mixture models for real-time tracking", Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pages 246-252, 1999.
   [2] J. Zhong and S. Sclaroff, "Segmenting Foreground Objects from a Dynamic, Textured Background via a Robust Kalman Filter", Proc. IEEE Conf. on Computer Vision, pages 44-50, 2003.
   Note: this project was offered to Mr. Lih Wern HIEW as a BE(SE) project in 2007.  Click here to see Hiew's work.
   
   
4. Motion Segmentation
   This project has similar applications as the previous one, except that a different approach would be adopted. Almost any scene is composed of a few foreground objects and a background. Given that we have a movie of a few moving objects in the scene, we can use their optical flow to identify and track the moving object. Not only so, if the moving objects are correctly identified, we could recreate a new movie with these objects removed.

   See for instance the websites below: motion segmentation; an example showing the filling-in of a moving subject.
   

5. Temporal-Spatial Reasoning on Weather Radar Images.
   This project is about temporal-spatial reasoning with incomplete information, in this case weather radar images, to predict time of rain front hitting a certain point within the metro area. This project will be a joint supervision with A. Prof. Mark Reynolds.
   Some useful links:
   A brief introduction to the field
   Current weather radar images in Perth
   
   
   

Return to the 4th year project list