Tutorials
The role of the tutorials is to provide a platform for a more intensive scientific exchange amongst researchers interested in a particular topic and as a meeting point for the community. Tutorials complement the depth-oriented technical sessions by providing participants with broad overviews of emerging fields. A tutorial can be scheduled for 1.5 or 3 hours.
Intelligent Vision Systems: Techniques and Ethics
Instructor
|
Joanna Isabelle Olszewska
School of Computing and Engineering, University of the West of Scotland
United Kingdom
|
|
|
|
Brief Bio
Joanna Isabelle Olszewska is a British Computer Scientist. She is an Assistant Professor (Lecturer) with UWS, UK, and leads research in Algorithms and Softwares for Intelligent Vision Systems. She is a member of the IEEE Global Initiative for Ethical Considerations in Artificial Intelligence and Autonomous Systems. She is an ACM Distinguished Speaker and has given talks, e.g. at the University of Cambridge, at conferences such as ICRA, and at events such as EPSRC/BMVA Technical Days and DDD Scotland, ACM Future Worlds as well as interviews, e.g. for the BBC Lunch Time 'Women in Engineering' Program. She has been TPC member of over 70 international conferences such as IJCAI and chaired over 60 conference/workshop sessions, e.g. at IROS.
|
Abstract
Intelligent Vision Systems, which are systems able to automatically process visual inputs such as raw still pictures or live video feeds, whatever they are equipped with camera(s) or directly access image databases, have become ubiquitous in our Society. Indeed, they can be found in a multitude of real-world applications such as video surveillance, m-health services, drones, companion robots, etc. Therefore, such intelligent vision systems must be both efficient and ethical. Thus, this tutorial introduces the topic of intelligent vision systems in light of the main technical and ethical challenges in that research field and the developed solutions and standards based on explainable artificial intelligence and transparent computer vision approaches.
Keywords
Explainable AI (XAI), Transparency and Ethical Issues, Privacy, Safety and Security, Image and Video Processing, Image and Video Analysis and Understanding, Pattern Recognition, Vision and Perception, Machine Learning, Knowledge Representation and Reasoning, Robotics, Autonomous Systems, Intelligent Agents.
Aims and Learning Objectives
This tutorial aims to present the ‘why’ and ‘how’ to develop reliable intelligent vision systems deployed in constrained and unconstrained environments.
Participants are expected to acquire new perspectives about intelligent vision systems’ challenges and their related solutions. In more detail, the objectives of this tutorial are:
I) To appreciate intelligent vision systems’ challenges in terms of performance and compliance;
II) To understand the corresponding solutions for the intelligent vision systems’ design;
III) To get new trends and future directions of the Intelligent Vision Systems research and development.
Target Audience
This tutorial is intended for a broad spectrum of participants both from academia and industry.
Prerequisite Knowledge of Audience
None
Detailed Outline
The tentative list of the topics covered by this tutorial is:
a) Intelligent Vision Systems: Definition & Applications
b) Technical Challenges of Intelligent Vision Systems
c) Ethical Challenges of Intelligent Vision Systems
d) Solutions and Standards