Indicative Data: Extracting 3D Models of Cities from Unavailability and Degradation of Global Navigation Satellite Systems (GNSS)

3-Dimensional (3D) models of cities are beneficial or even essential for many applications, including urban planning/development, energy demand/consumption modelling, emergency evacuation and responses, lighting simulation, cadastre and land use modelling, flight simulation, positioning and navigation (particularly for autonomous cars in urban canyons and disabled users requiring accessibility), and Building Information Modelling (BIM). Despite the importance of the 3D models, they are not available or being updated frequently for many areas/cities. This can be due to the process of generating and updating (by current technologies such as LiDAR (Light Detection and Ranging)) being computationally and financially expensive, time-consuming, and requiring frequent updates due to the dynamic nature of cities. This fellowship will propose and implement a crowdsourcing-based approach to create accurate 3D models from the free to use and globally available data of Global Navigation Satellite Systems (GNSS). The effects of urban features, such as buildings and trees, on GNSS signals, i.e. signal blockage and obstruction, and attenuation, will help to recognise the shape, size, and materials of urban features, through the application of statistical, machine learning (ML) and artificial intelligence (AI) techniques. The use of freely accessible raw GNSS data, which can be accessed on any current Android device, will enable the production of up to date 3D models at no or low cost, of particular value in developing regions where these models are not currently available.

GNSS is the most widely used positioning technique because of free-to-use, privacy-preserving, and globally available signals. However, GNSS signals can be blocked, reflected and/or attenuated by objects, e.g. trees, buildings, walls and windows. While blockage, attenuation and reflection of GNSS signals are common in urban canyons and indoors, making the positioning unreliable, inaccurate or impossible, the affected received signals can act as an indicator of the structure of the surrounding environments. This means, for example, if the signals are blocked or attenuated, then the size and shape of the obstacles or the type of media/material the signals have gone through or been reflected by can be understood. This needs the precise locations of satellites, and the receiver, and also predicted signal strength level at each location and time. The crowdsource-based framework, i.e. a mobile app for data capture and a web mapping application for upload of GNSS raw data, will allow the project to have well-distributed data both in space and time. This will ultimately lead to higher quality (more spatially and temporally accurate, complete, precise) 3D models. However due to the complexity of data, as neither the receiving mobile devices nor the broadcasting satellites are fixed, some novel data mining techniques, based on already existing statistical, ML, and AI techniques, need to be developed during this fellowship. They will handle the high volume, the velocity of change, and the complexity of the spatio-temporal GNSS raw data with high levels of veracity. The spatio-temporal patterns will be used for creating and updating the 3D models of cities at a high level of detail (LoDs), i.e. approximating the façade and the building materials, e.g. windows, from which the signals are reflected or have gone through. The 3D models will feed into 3D-mapping aided GNSS positioning (and integrated with other signals e.g. WiFi) which can ultimately provide more continuous and accurate GNSS positioning in urban canyons and indoors.

This fellowship will provide a novel perspective which perceives lack and degradation of data as an "indicative" source of data, which can be re-applied by other disciplines. The success of this fellowship will help me to establish myself as an internationally recognised leader in the area of spatial data science.

The success of this project will enable several disciplines and sectors to create, update, and (re-)use 3D models of the cities only requiring GNSS raw data, which is globally available and free-to-use. Such disciplines and sectors may include:

Energy: Currently there are several projects which run a 3D building stock model to estimate and predict energy consumption. Such 3D models are mostly based on expensive LiDAR and Ordnance Survey Mastermap. This project will provide up-to-date 3D models that are free-to-create and easy to update.
Positioning and Navigation: The primary application of GNSS is for positioning and navigation. While GNSS is the most-widely used a positioning technology with an estimated market of at £2.3B in the UK, its functionality is mainly limited to outdoors. While 3D-mapping aided GNSS positioning provides very impressive results, its accuracy and usability depend on the availability and the quality of the 3D models. This project will develop a recursive platform where GNSS RSS patterns will feed into 3D modelling and 3D models will feed into "shadow-matching" positioning services. It is also envisaged that positioning service can be integrated with 3D modelling and provides with a Simultaneous Localisation and Mapping (SLAM) service, based on GNSS raw data.
The indoor positioning and navigation applications currently are based on other positioning technologies such as Wireless Local Area Network (WLAN), Radio Frequency IDentification (RFID), Cameras, Bluetooth Low Energy (BLE), etc., none can yet provide a globally available, privacy preserving service at minimum cost to users associated with infrastructure development/installation and maintenance, or in another word a "GNSS-like" service. The success of the project will provide a seamless (indoor/outdoor) positioning and navigation service, resulting in UK industry being at the forefront of the indoor positioning market.
The seamless positioning service the project can provide, will be beneficial not only for navigation services, i.e. the biggest revenue generator of Location Based Services (LBS) industry, but also for many other services including healthcare services worldwide will benefit from a continuous, accurate positioning service improving the ability to respond quickly to emergencies, saving or improving the quality of many lives. The US statistics state 10,000 lives per year could be saved if accurate (50m horizontally) indoor location was attached to 67% of emergency calls.
Policy makers: The outcomes of this research can be utilised by policy makers (via UCL Public Policy team, Uber, OS), such as urban planners and disaster managers. E.g. with a facility to rapidly and freely generate/update the 3D model of the cities they can have a better understanding of the current situation (e.g. disaster) to manage it better. This also promotes UK involvement with European GNSS, Galileo, or mandating revisions to positional requirements for emergency calls, security and tracking related applications, in order to improve services (e.g. E112).
Public: The crowdsourcing is at the heart of the project (promoted by public engagement events and school visits). The public will contribute data and will see the 3D model of their surrounding. individuals will benefit from accessing more accurate positioning/LBS services, e.g. navigation, inside buildings.
Research: The step-changing view of this project, i.e. considering lack of data (e.g. blockage of signals) as indicative data itself (e.g. size and shape of the blocking building) can be applied by many other disciplines, such as statistics and data science. This is particularly important in the era of big data, where data might not be captured for the specific use of the application and so the level of availability and uncertainty could vary. Also, the disciplines including data science, positioning and navigation, transportation, energy, and citizen science can extend their research.