Week 1 |
Introductory lecture
Introduces the module, outlining its relevance to the field and connections to other topics. It provides an overview of the content structure, key references, and assessment details. |
Week 2 |
Computer Vision Fundamentals
Establish a strong foundation in computer vision to understand how machines perceive and interpret visual information. Appreciate the importance of enabling computers to analyse images and videos, setting the stage for learning advanced techniques that solve real-world problems. Explore the transformative impact of computer vision across various industries, fostering an appreciation for its potential to revolutionise technology. |
Week 3 |
Feature Detection and Description
Master feature detection techniques like SIFT, SURF, and ORB to enable recognition of shapes and textures in images. Understand why detecting key features is critical for interpreting visual data and how it underpins more advanced computer vision tasks. Develop the ability to identify and describe significant elements within images, paving the way for complex analysis and recognition systems. |
Week 4 |
Image Segmentation Techniques
Explore methods for dividing images into meaningful segments to understand their structure and content. Learn why segmenting images is essential for tasks like object detection and scene understanding. Gain insights into the importance of isolating regions of interest, which is foundational for developing sophisticated computer vision applications. |
Week 5 |
Advanced Object Detection
Delve into cutting-edge object detection algorithms like Mask R-CNN, YOLO, and Faster R-CNN to detect and classify objects within images. Understand why accurate object detection is vital for applications ranging from autonomous vehicles to surveillance. Develop the skills to implement systems that can identify multiple objects in real time, addressing challenges in dynamic environments. |
Week 6 |
Deep Learning Foundations
Discover the power of deep learning in computer vision, focusing on Convolutional Neural Networks (CNNs). Understand why deep learning has revolutionised image analysis and recognition tasks. Learn to leverage neural networks to extract complex features, enabling advanced capabilities in visual perception and interpretation. |
Week 7 |
Vision Transformer Architectures
Explore transformer-based architectures like Vision Transformers to advance beyond traditional CNNs. Understand why transformers offer a novel approach to image analysis, capturing global relationships within visual data. Grasp the significance of these models in pushing the boundaries of what's possible in computer vision. |
Week 8 |
Implementing Deep Learning Frameworks
Harness the power of frameworks like TensorFlow and PyTorch to implement complex deep learning models. Understand why these tools are essential for efficient development and experimentation in computer vision. Develop practical skills to build, train, and optimise neural networks, empowering you to bring sophisticated vision systems to life. |
Week 9 |
Transfer Learning and Network Adaptation
Apply transfer learning to adapt pre-trained networks for new tasks with limited data. Understand why leveraging existing models accelerates development and improves performance in complex applications. Learn to fine-tune networks, saving time and resources while achieving high accuracy in specialised computer vision tasks. |
Week 10 |
Real-Time Processing and Multi-Object Tracking
Equip yourself with techniques for processing video streams and data in real time, vital for applications like surveillance and autonomous systems. Understand why speed and latency are critical in dynamic environments. Learn to implement multi-object tracking, addressing the challenges of detecting and following multiple entities simultaneously in live settings. |