| CODE | SCE4104 | ||||||||||||
| TITLE | Practical Applications in Computer Vision | ||||||||||||
| UM LEVEL | 04 - Years 4, 5 in Modular UG or PG Cert Course | ||||||||||||
| ECTS CREDITS | 5 | ||||||||||||
| DEPARTMENT | Systems and Control Engineering | ||||||||||||
| DESCRIPTION | This study-unit introduces practical applications in Computer Vision. It builds upon the early concepts of image analysis such as image enhancement, image segmentation and representation by applying these concepts to practical vision problems. In this unit, students will learn how to use Python and the OpenCV library to read, analyse and process images with the scope of extracting features from images. Practical applications including object detection, face detection and image stitching will be discussed. The unit will also introduce the student to the skills required to work with video data, covering topics such as optical flow with applications in object tracking. The unit will then present deep learning applications in computer vision. Study-unit Aims: To provide: - The skills required to read and process image and video data using Python and the OpenCV library; - The theoretical principles underlying feature extraction and object detection; - The theoretical principles underlying optical flow and object tracking; - An introduction to deep learning applications in computer vision. Learning Outcomes: 1. Knowledge & Understanding By the end of the study-unit the student will be able to: - Given an image, the student will be able to explain and demonstrate the principles of feature extraction applicable to the image, including the extraction of corners, edge and contours; - Given video data, the student will be able to explain and demonstrate the principles of object tracking including optical flow, MeanShift and CamShift tracking; - Given a computer vision problem, describe how deep learning approaches can be used to solve the problem. 2. Skills By the end of the study-unit the student will be able to: - Extract features such as corners, edges and contours from image data and use the selected features to solve object detection applications; - Apply the principles of object tracking to track a specific object across a video stream; - Apply deep learning algorithms to solve classification and object detection; - Program computer vision algorithms in Python and OpenCV. Main Text/s and any supplementary readings: - Computer Vision, A Modern Approach. Second Edition - Forsyth and Ponce, Pearson Publishers (2012) - Ian Goodfellow and Yoshua Bengio and Aaron Courville. Deep Learning. The MIT Press (2016) |
||||||||||||
| ADDITIONAL NOTES | Pre-Requisite Study-Unit: SCE3204 | ||||||||||||
| STUDY-UNIT TYPE | Lecture, Independent Study, Project and Tutorial | ||||||||||||
| METHOD OF ASSESSMENT |
|
||||||||||||
| LECTURER/S | 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. |
|||||||||||||