Home // VISUAL 2016, The First International Conference on Applications and Systems of Visual Paradigms // View article

Selecting Adequate Aerial Perceptual Functions with Fuzzy Logic

Authors:
Christian Hellert
Peter Stütz

Keywords: Perception functions; fuzzy logic; algorithm selection; algorithm ranking; expert knowledge

Abstract:
The increasing interest in higher automation of unmanned aerial vehicles (UAV) rises the challenge of implementing sophisticated perception functions. Since such functions, whether being used for navigational (e.g., sense & avoid) or surveillance purposes (e.g., object detection & tracking), are heavily influenced by environmental conditions. Hence, a careful selection and parametrization of the perception functions during flight is required to maintain perceptual efficiency on-board the UAV. This paper introduces a method to predict the performance of perception functions, allowing a ranking for algorithm selection. The proposed method uses expert knowledge to model the influence of the environment on the perception functions using fuzzy logic. An evaluation of the proposed method is performed with an aerial vehicle detection algorithm on an imagery dataset, generated from virtual simulation, taking into account fog density and cloud cover. The results show that the method can predict the algorithms performance in general and has the advantage of expressive modelling of the expert knowledge.

Pages: 8 to 12

Copyright: Copyright (c) IARIA, 2016

Publication date: November 13, 2016

Published in: conference

ISSN: 2519-8645

ISBN: 978-1-61208-520-3

Location: Barcelona, Spain

Dates: from November 13, 2016 to November 17, 2016