Most of the state-of-the-art vision systems operate in 2D dimensions treating the world as just a set of pixels. Such models are missing a dimensional source of information as our world is three-dimensional. Understanding this extra dimension has allowed humans to build an intuition of how objects will behave in the environment. Adrian's research project aims to replicate this in autonomous systems to understand the dynamics of a wide range of environments with different types of objects.
Adrian Salazar-Gomez is a PhD student at the EPSRC Centre for Doctoral Training in Robotics and Autonomous Systems at the Edinburgh Centre for Robotics. Adrian's research interests lie broadly within computer vision, machine learning, and autonomous systems. Adrian's goal is to enable autonomous systems to perceive the world as humans do -- with a special focus on understanding the geometry of the environments and their dynamics, given visual observations. Additional interests include understanding neural networks, building databases, common-sense reasoning, and the intersection between robotics and agriculture.
Happy to chat:
"Happy to chat about anything that you find interesting in my research area, just send me an email to:
Adrian's Google scholar profile:
Link to Adrian's Google Scholar