TY  - GEN
KW  - Data Study Group; The Alan Turing Institute; Leeds Institute for Data Analytics
TI  - Data Study Group Final Report:
Ordnance Survey Northern Ireland (OSNI):

Leveraging LiDAR and Street View data for road feature
detection with OSNI
UR  - https://doi.org/10.5281/zenodo.6498764
EP  - 77
AV  - public
ID  - discovery10183512
N1  - Creative Commons Attribution 4.0 International (CC BY 4.0) Licence (https://creativecommons.org/licenses/by/4.0/).
Y1  - 2022/04/27/
PB  - Zenodo
A1  - Data Study Group Team
CY  - Genève, Switzerland
N2  - The Ordnance Survey of Northern Ireland (OSNI) mission is to provide high quality geospatial data. Historically this has been for 2D mapping, but modern survey techniques and increasing user requirements have shifted focus toward 3D data. Since 2019, OSNI has operated a vehicle mounted Mobile Mapping System (Leica Pegasus:Two Ultimate Mobile Mapping System) across Northern Ireland capturing 3D Point Cloud data and spherical street view imagery.

The range of potential applications is significant, including urban planning, asset identification and management, automating identification of road sign changes for navigation and transport network datasets, identifying feature locations such as scenic views, drainage, potholes and road surface quality, street furniture maintenance, 5G network planning and managing autonomous vehicles. While availability and accessibility of this kind of raw data is improving, there are significant technical challenges in deriving insights from the richness of this dataset.

To address these challenges this project seeks to explore the potential of OSNI?s highly detailed Light Detection and Ranging (LiDAR) and imagery data via Machine Learning (ML) and data science methods, with a focus on developing pipelines to visualise, classify and identify road features like drainage which could potentially help various government authorities better monitor road infrastructure. There are many other potential applications for the sort of data OSNI collects, and we hope some of the pipelines and visualisations explored below can aid broader applicability. Below are the results from each of the streams of work conducted.
ER  -