BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//University of Liverpool Computer Science Seminar System//v2//EN
BEGIN:VEVENT
DTSTAMP:20260409T110343Z
UID:Seminar-dept-473@lxserverA.csc.liv.ac.uk.csc.liv.ac.uk
ORGANIZER:CN=Lutz Oettershagen:MAILTO:Lutz.Oettershagen@liverpool.ac.uk
DTSTART:20190122T130000
DTEND:20190122T140000
SUMMARY:School Seminar Series
DESCRIPTION:John Murray: End to End Analysis of Large 3D Geospatial Datasets with GPUs\n\nLocation intelligence is key to understanding many aspects of modern life including property insights, environmental monitoring, disaster management and prevention, traffic flows, customer behaviour etc. In order to build deep learning models, large volumes of data from satellite images, 3D sensors, GPS enabled devices, social media and many other sources need to be merged using computationally intensive coordinate conversion and matching.\n\n\n\nIn Europe, the property insurance sector has been disrupted by growing use of comparison websites which requires real time quotations to be provided. Fusion Data Science has developed a solution, using 3D deep learning CNNs, to estimate risk factors from colour 3D virtual models of individual properties.\n\n\n\nThe talk will cover the entire process, using GPUs, from processing raw data, merging source, generating & labelling voxel cubes for training, building the models and inference.\n\n\n\nThe session will conclude with a demonstration with live data.\n\nhttps://www.csc.liv.ac.uk/research/seminars/abstract.php?id=473
LOCATION:Ashton Lecture Theater
END:VEVENT
END:VCALENDAR