This course covers the essentials for getting started with developing computer vision systems and focuses on how computer vision can be applied to solve real-world problems. We cover the basics of how images are formed, how to deal with multiple views of the same scene, how useful features and representations can be extracted from images. We also look at tasks such as 3D reconstruction, detecting objects, estimating the pose of humans and animals, and captioning images.
This course provides an introduction to the core principles of modern deep neural networks, with a strong focus on practical applications. It is designed for students who may have experience in maths and statistics, but have little to no prior exposure to deep learning concepts. The aim is to build a solid foundation in deep learning, bridging the gap between their existing knowledge and this specialised area.