Computer Vision was massively reshaped with recent advances in Deep Learning, which took over some of the most complex tasks and problems. On the other hand, Classical approaches for image analysis still play a dominant role in various real-world applications and can provide an important boost for the design of Deep Learning pipelines.
This course will outline the CV fundamentals from a formation of image and role of the transformations to basic concepts in segmentation and tracking. On the other hand, we will try to link these Classical approaches to their siblings in Deep Learning to highlight when various methods may be more practical.
Computer vision, Filters, Optical Flow, Deep Learning, Image Filtering, Tracking.
Dr. Mykola Maksymenko
Research Lead at SoftServe with focus on Artificial Intelligence, Complex systems modeling and Optimization problems arising in various Enterprise applications. He holds a PhD in Theoretical Physics and has more than 10 years of academic and industry research experience with previous posts at Max Planck Society in Germany and Weizmann Institute of Science in Israel.
Fields of interests: physics of deep learning, quantum machine learning.
Dr. Viktoriia Sharmanska
Imperial College London, United Kingdom
Viktoriia is passionate about designing intelligent systems that can learn concepts from visual data using machine learning models. She got her PhD in Computer Vision and Machine Learning from IST Austria, and MSc in Applied Mathematics from Taras Shevchenko National University of Kyiv, Ukraine. Since 2015, she’s a visiting research fellow at the University of Sussex, UK working on cross modal learning with privileged information. In October 2017, she joined Imperial College London as a research fellow, where she’s working on action and emotion recognition in video data using deep learning.
Fields of interests: Computer Vision and Machine Learning.