Unraveling Insights About Places with Deep Learning Computer Vision
Images are a rich source of information about our environment, opening doors to nuanced understandings and insights. In this engaging talk, we will delve into the power of deep learning and its ability to revolutionise how we perceive and analyse places.
In this talk, I will share insights from our work where we utilised AI to scrutinise over 200,000 images from Scenic-Or-Not, teaching an algorithm to identify and quantify the beauty of various places in Great Britain. Furthermore, I will introduce the next steps at Beautiful Places AI, where we aim to expand our datasets globally, enhancing our understanding of the correlation between beautiful environments, societal well-being, and economic prosperity.
Additionally, the talk will delve into the application of Deep Learning at Zoopla and HomeTrack, revealing how images and property data are synergised to unveil significant insights into people’s preferences and property values. This talk will illuminate the revolutionary potential of deep learning computer vision in transforming our analytical approach to places and properties.