Computer Vision is an important field of Artificial Intelligence concerned with automatically extracting useful information from images or videos. The explosive growth in digital imaging technologies, vision datasets and deep learning makes the problems of automated image interpretation even more exciting and more relevant than ever. This course introduces students to fundamental problems in computer vision and foundational techniques for solving them. Topics covered in detail include: image formation, image filtering, camera geometry, thresholding and image segmentation, edge, point and feature detection, geometric frameworks for vision, single view and two views geometry, 3D visual reconstruction, camera calibration, stereo vision, image classification, object recognition, deep learning and neural networks. The course features extensive practical components including computer labs that provide students with the opportunity to practice and refine their skills in computer vision.
Learning Outcomes
Upon successful completion, students will have the knowledge and skills to:
- Understand and apply basic knowledge, methods and skills in image processing and computer vision.
- Identify, formulate and solve problems in image processing and computer vision.
- Analyse, evaluate and examine existing practical computer vision algorithms.
- Design and develop practical and innovative image processing and computer vision applications or systems.
- Communicate effectively to both specialist and non-specialist audiences, explaining concepts related to visual information processing systems.
- Conduct themselves professionally and responsibly in the areas of computer vision, image processing and deep learning.