|
|
|
|
|
2009-2011 Projects 2008 Projects 2007 Projects 2006 Projects 2005 Projects 2004 Projects
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:
The 3D model of a static scene can be reconstructed from a sequence of images taken from different locations and viewing orientations in space. One of the common approaches to recovering scene structures is to divide the image sequence into sets of image triplets and compute the so-called trifocal tensor, which embodies the camera parameters and geometry. In this project, we will investigate a method of computing the optimal estimate of the trifocal tensor in the presence of image noise and outliers (incorrectly tracked image features). The project will involve the study of different algorithms for trifocal tensor computation and camera auto-calibration. An existing KLT feature tracker will be used for feature detection and tracking.
Image rectification is a process to align two images of a scene so that all the matching feature points in the two images fall onto the same horizontal or vertical scanlines. Image rectification is a necessary step for generating dense matching feature points for scene reconstruction in stereo vision. In this project, we will investigate recent techniques in image rectification reported in the literature and compare their effectiveness in terms of distortion and resampling effect.
Dynamic programming techniques are used to find optimal strategies in many different situations. Perhaps the simplest is that of a traveller trying to get from A to B along a network of roads with multiple intersections. At each intersection, a choice of which way to go is needed. The aim is to find the shortest path. Dynamic programming is a method of posing such problems so as to minimize computation. In some cases, it produces closed form solutions. It is used in inventory control, scheduling problems and many other real-world applications.
In this project, the student will learn the basic ideas of dynamic programming and apply them to a number of games including the games of Pig, Flip and Flip-flop, and the 37 Game.
The aim of this project is to mosaic images taken by a hand-held video camera; in particular, the research focus will be on the scanner video mosaicing technqiue proposed by Peleg and Herman. The project will require the student to have some basic knowledge in projective geometry (e.g., the plane-to-plane homography) and good background in mathematics. The project will be fun to those who like to capture and process video images. If interested, please refer to the paper by Peleg and Herman [1] below and follow the literture for other related papers.
References:Note: This project was taken by Chi Chiu CHENG in 2003 as a MSc (course work) project.
Return to the 4th year project list