UAS.pdf (2.23 MB)
Machine vision for UAS ground operations: using semantic segmentation with a bayesian network classifier
journal contribution
posted on 2017-05-23, 13:24 authored by Matthew CoombesMatthew Coombes, Will Eaton, Wen-Hua ChenWen-Hua ChenThis paper discusses the machine vision element of a system designed to allow Unmanned Aerial System (UAS) to perform automated taxiing around civil aerodromes, with only a monocular camera. The purpose of the computer vision system is to provide direct sensor data which can be used to validate vehicle position, in addition to detecting potential collision risks. In practice, untrained clustering is used to segment the visual feed before descriptors of each cluster (primarily colour and texture) are used to estimate the class. As the competency of each individual estimate can vary dependent on multiple factors (number of pixels, lighting conditions and even surface type). A Bayesian network is used to perform probabilistic data fusion, in order to improve the classification results. This result is shown to perform accurate image segmentation in real-world conditions, providing information viable for localisation and obstacle detection.
Funding
This work was supported by the U.K. Engineering and Physical Sciences Research Council (EPSRC) Autonomous and Intelligent Systems programme under the grant number EP/J011525/1 with BAE Systems as the leading industrial partner. The work greatly benefits from the data set collected from an airfield provided by BAE Systems and technical advice provided by the technical officer Rob Buchanan.
History
School
- Aeronautical, Automotive, Chemical and Materials Engineering
Department
- Aeronautical and Automotive Engineering
Published in
Journal of Intelligent and Robotic Systems: Theory and ApplicationsPages
1 - 20Citation
COOMBES, M., EATON, W.H. and CHEH, W.-H., 2017. Machine vision for UAS ground operations: using semantic segmentation with a bayesian network classifier. Journal of Intelligent and Robotic Systems, 88(2-4), pp. 527-546.Publisher
Springer / © The AuthorsVersion
- VoR (Version of Record)
Publisher statement
This work is made available according to the conditions of the Creative Commons Attribution 4.0 International (CC BY 4.0) licence. Full details of this licence are available at: http://creativecommons.org/licenses/ by/4.0/Acceptance date
2017-03-16Publication date
2017Notes
This is an Open Access Article. It is published by Springer under the Creative Commons Attribution 4.0 International Licence (CC BY). Full details of this licence are available at: http://creativecommons.org/licenses/by/4.0/ISSN
0921-0296eISSN
1573-0409Publisher version
Language
- en