Home // FUTURE COMPUTING 2020, The Twelfth International Conference on Future Computational Technologies and Applications // View article

Guillaume Khenchaff’s Measure for Clustering Method

Authors:
Spinoza Paula Niels
Rahajaniaina Andriamasinoro
Jessel Jean-Pierre

Keywords: Salient object; a contrario grouping; probabilistic quality measurement

Abstract:
“a contrario” is one of the techniques for tracking objects in real time. However, decomposition methods may still fail to effectively group salient objects according to its movement on the real scene. In this paper, we present an approach for optimizing the "a contrario" grouping method. We introduce a new clustering framework using the probabilistic quality measurement technique, which measures the degree of dependence between the mobile group accepted by the Number of False Alarms (NFA) measure and the group considered to be static in the binary tree. We demonstrate the effectiveness of our method with different situations in uncontrolled environments. We also show its applicability with the Simultaneous Localization And Mapping and Moving Objects Tracking (SLAMMOT) approach.

Pages: 1 to 6

Copyright: Copyright (c) IARIA, 2020

Publication date: April 26, 2020

Published in: conference

ISSN: 2308-3735

ISBN: 978-1-61208-779-5

Location: Nice, France

Dates: from October 25, 2020 to October 29, 2020