Share Email Print
cover

Proceedings Paper • new

Comparison of two classifiers based on neural networks and the DTW method of comparing time series to recognize maritime objects upon FLIR images
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Infrared image recognition by means of FLIR cameras (forward-looking infrared) is one of the elements of the recognition of the maritime situation and it supports in many situations the creation of so-called maritime picture. This paper presents results of two FLIR image classifiers research. The first part presents the use of neural networks to classify images of maritime objects, while the second part presents the classifier using the time series comparison method called the DTW (data time warping). The neural network is a three-layered artificial neural network (feed forward). Both classifiers use the histograms of vertical projection of pre-processed FLIR images as input data. These histograms are created as a result of FLIR color images processing, including, among others, transformation of color images into grayscale images, grayscale images segmentation using the Otsu algorithm, rescaling, centering and leveling. In the final part of the paper preliminary test results of the both classification methods for a set of maritime objects FLIR images registered in the Baltic Sea are presented.

Paper Details

Date Published: 27 March 2019
PDF: 11 pages
Proc. SPIE 11055, XII Conference on Reconnaissance and Electronic Warfare Systems, 110550V (27 March 2019); doi: 10.1117/12.2524918
Show Author Affiliations
Tadeusz Pietkiewicz, Military Univ. of Technology (Poland)
Katarzyna Sikorska-Łukasiewicz, Military Univ. of Technology (Poland)


Published in SPIE Proceedings Vol. 11055:
XII Conference on Reconnaissance and Electronic Warfare Systems
Piotr Kaniewski, Editor(s)

© SPIE. Terms of Use
Back to Top