| CODE | SCE5205 | ||||||||||||||||
| TITLE | Computer Vision | ||||||||||||||||
| UM LEVEL | 05 - Postgraduate Modular Diploma or Degree Course | ||||||||||||||||
| ECTS CREDITS | 5 | ||||||||||||||||
| DEPARTMENT | Systems and Control Engineering | ||||||||||||||||
| DESCRIPTION | This study-unit deals with the different methods with which information can be extracted from images. This includes an introduction to elementary image processing techniques such as mean and median filtering as tools for removing noise, the use of histograms to enhance the quality of the image and edge detection to extract the contours of objects from scene images, segmentation techniques such as binarisation, region growing and RANSAC through which the scene may be subdivided into meaningful parts. The study-unit also deals with a higher level processing of images including feature characterisation and matching techniques which can then be used for image search as well as motion analysis. The study-unit focuses computer vision applications in fields related to control systems engineering such as motion analysis for autonomous robotic control and the use of vision as a element for feedback in a control system. To this effect, the study-unit will also cover topics related to the geometry of vision. Study-Unit Aims The aim of this study-unit are to: - present a scale-space representation of an image; - distinguish between different segmentation algorithms and motivate their use according to application; - present a formal theory for edge and corner detection; - present the geometry of vision; - distinguish between the different feature characterisation algorithms and motivate their use in image matching applications; - distinguish between different motion analysis algorithms; - present contour model algorithms; - present the OpenCV as a programming language for computer vision applications. Learning Outcomes 1. Knowledge & Understanding By the end of the study-unit the student will be able to: - explain the theory of scale-space representation and identify its applicability; - explain and distinguish between different segmentation techniques, selecting appropriate techniques according to the problem at hand; - comprehend and select the appropriate feature characterisation for use in motion analysis or image search; - explain the camera model geometry and select appropriate computer vision algorithms for use in control systems. 2. Skills By the end of the study-unit the student will be able to implement algorithms that: - select, explain and design a computer vision system; - design and implement algorithms for feature characterisation such as moment features boundary coding, edge histograms and the scale invariant feature transform; - design and implement algorithms for motion analysis including the Kanade-Lucas-Tomasi feature tracker and the use of multiple hypothesis tracking; - implement contour modelling algorithms, e.g. active contours and active shape models; - perform camera calibration to use vision as a sensor in the real 3D world. Students will also acquire skills in implementing these algorithms using OpenCV libraries. Main Text/s and any supplementary readings Main Texts: - Computer Vision: Algorithms and Applications- Richard Szeliksi, Springer - Davies, E.R., 2004. Machine vision: theory, algorithms, practicalities. Elsevier. - Forsyth, D.A. and Ponce, J., 2003. A modern approach. Computer Vision: A Modern Approach, pp.88-101. Supplementary Readings: - Trucco, E. and Verri, A., 1998. Introductory techniques for 3-D computer vision (Vol. 201). - Open CV 2: Computer Vision Application Programming Cookbook, Laganiere. |
||||||||||||||||
| STUDY-UNIT TYPE | |||||||||||||||||
| METHOD OF ASSESSMENT |
|
||||||||||||||||
| LECTURER/S | Alexandra Bonnici Stefania Cristina |
||||||||||||||||
|
The University makes every effort to ensure that the published Courses Plans, Programmes of Study and Study-Unit information are complete and up-to-date at the time of publication. The University reserves the right to make changes in case errors are detected after publication.
The availability of optional units may be subject to timetabling constraints. Units not attracting a sufficient number of registrations may be withdrawn without notice. It should be noted that all the information in the description above applies to study-units available during the academic year 2024/5. It may be subject to change in subsequent years. |
|||||||||||||||||