Department of Computer Science, Unit Catalogue 2011/12 |
|
 Credits:
| 6 |
| Level:
| Masters UG & PG (FHEQ level 7) |
| Period: |
Semester 2 |
| Assessment:
| CW 50%, EX 50% |
| Supplementary Assessment: | Supplementary assessment information not currently available (this will be added shortly) |
| Requisites:
| |
| Description:
| Aims: To give students an advanced level understanding of current research issues in computer vision. To focus upon computer vision methods, computer vision theory, evaluation of methods and modeling vision problems. To study the latest applications of computer vision in traditional areas of science, engineering, etc, and also in new applications for entertainment, education, smart homes, etc. Learning Outcomes: Students will be able to: * Obtain an in-depth understanding of computer vision theory and methods in state-of-the-art computer vision research; * Appreciate a broad range of contemporary Computer Vision; * Develop a systematic understanding of vision software development; * Understand the interdisciplinary nature of advanced computer vision and to be able to combine theories and principles to achieve correctly engineered simulations; * Distinguish low-level from high-level Computer Vision methods; * Describe edge detection as a linear filter and distinguish between linear filtering and morphology; * Describe multi-camera geometry and understand it value in applications such as mosaicing and reconstruction; * Understand texture and segmentation, and the role of high-level models in recognition. Skills: Ability to apply modern methods and algorithms to vision solutions (T,F,A), wide knowledge of computer vision methods (T/F/A), communication skills (F/A). Content: Low level vision: Convolution and linear filtering, edge detection and blurring; the role of scale. Morphology. Texture descriptors. Multi-camera vision: Homographies, epipolar geometry, and the fundamental matrix. Mosaicing and 3D reconstruction. Segmentation: Hough transforms, unsupervised clustering, scale sieves. Recognition: The role of prior models: templates, geometry, and statistics. |
| Programme availability: |
CM50208 is Optional on the following programmes:Department of Computer Science
|