Skip to main page content - your browser does not fully support our CSS, or is text-only.

Computing Science and Maths Seminars, 2019/2020

Autumn 19 image

Seminars will take place in Room 4B96,  Cottrell Building, University of Stirling. Normally, from 15.00 to 16.00 on Friday afternoons during semester time, unless otherwise stated. For instructions on how to get to the University, please look here.

If you would like to give a seminar to the department in future or if you need more information,  
please contact the seminar organisers, Dr. Sandy Brownlee (sbr@cs.stir.ac.uk) and Dr. Wen-shin Lee (wsl@cs.stir.ac.uk)

Autumn 2019

Date Speaker Title/Abstract
Friday
13th September
Sarah Thomson TBA

Friday
20th September
Dr Ross Kelly, Department of Applied Mathematics, Liverpool John Moores University TBA
Friday
27th September
Available slot TBA
Friday
4th October
Dr Scott Denholm, SRUC TBA
Friday
11th October
Dr Marc Roper, Computer and Information Sciences, University of Strathclyde TBA
Friday
18th October
Internal events No seminar this week
Friday
25th October
Reading week No seminar this week
Friday
1st November
Available slot
Friday
8th November
Prof Annie Cuyt, University of Antwerp, Belgium TBA
Friday
15th November
Available slot
Friday
22nd November
Winter graduations No seminar this week
Friday
29th November
Dr Andrea Berardi, The Open University TBA
Friday
6th December
Georgi Tinchev, University of Oxford Real-time LIDAR localization in natural and urban environments
Localization is a key challenge in many robotics applications. In this work we explore LIDAR-based global localization in both urban and natural environments and develop a method suitable for online application. We present a method capable of achieving state-of-the-art performance while being three times faster than previous approaches, as well as occupying 70\% less memory without a significant loss of performance. Our approach leverages efficient deep learning architectures capable of learning compact point cloud descriptors directly from 3D data. The method uses an efficient feature space representation of a set of segmented point clouds to match between the current scene and the prior map. We show that down-sampling in the inner layers of the network can significantly reduce computation time without sacrificing performance. Our experiments demonstrate a factor of three reduction of computation with marginal loss in localization frequency. We evaluate the proposed methods on nine scenarios from six datasets varying between urban, park, forest and industrial environments. The proposed learning method can allow the full pipeline to run on robots with limited computation payload such as drones, quadrupeds or UGVs as it does not require a GPU at run time.
[an error occurred while processing this directive]

Top image: Image and vision processing.
Courtesy of Dr. Deepayan Bhowmik.


This page is maintained by:
Computing Science and Mathematics
Faculty of Natural Sciences
University of Stirling, Stirling FK9 4LA
Tel: +44 1786 46 7421


© University of Stirling FK9 4LA Scotland UK • Telephone +44 1786 473171 • Scottish Charity No SC011159
Portal Logon

Forgotten login?

×