Satellite and aerial imagery for government

Introduction

High resolution satellite and aerial image data have become much more widely available over the past 10 years. Despite this, image data remains an underutilized source of information, especially in the public sector, because methods for extracting meaning from image data are not as straightforward as with numerical data.

We aim to leverage imagery to create new types of information for policy makers, which should in turn allow for more well-informed decisions around the provision of public services.

Research Areas

Hazardous Roads

Globally, approximately 1.3 million people die each year because of road traffic collisions (RTCs), and a majority of these deaths fall among vulnerable road users such as pedestrians and cyclists. In the UK, fatal or serious injuries occur on public roads every 16 minutes. In 2020, the United Nations General Assembly resolved to halve the number of global deaths and injuries from RTCs by 2030, noting that the overwhelming majority of these cases are preventable. To achieve this ambitious goal, new technologies and data will be required to enhance road safety experts’ implementation of RTC interventions.

We utilize unsupervised machine learning methods to extract nuanced meaning about how and where different types of RTCs occur.

Urban Canopies

Urban tree canopies are fundamental to mitigating the impacts of climate change within cities as well as providing other important ecosystem, health, and amenity benefits.

Mapping urban tree canopies can be a challenging task, but we are developing AI tools to create detailed maps of cities’ canopy structure from satellite and aerial imagery. With better maps of urban trees, researchers and local authorities will be able to build a clearer picture of the impacts of greenery on residents, prioritising planting where it is needed most.