Journal cover Journal topic
Journal of Sensors and Sensor Systems An open-access peer-reviewed journal
Journal topic

Journal metrics

CiteScore value: 3.5
CiteScore
3.5
SNIP value: 1.108
SNIP1.108
IPP value: 1.38
IPP1.38
SJR value: 0.434
SJR0.434
Scimago H <br class='widget-line-break'>index value: 13
Scimago H
index
13
h5-index value: 15
h5-index15
Download

Please read the editorial note first before accessing the article

Short summary
We have prepared an article that demonstrates one of the ways to recognize objects on the ground surface. This paper is a result of experimental data that were collected with unnamed aerial vehicles (UAVs) with synthetic aperture radar. Although UAV radar has a small monitoring area, we noted that such pictures can contain the steady features of the mutual arrangement between detected objects. We have constructed an artificial neural network that solves the tasks of group object recognition.
Articles | Volume 10, issue 1
J. Sens. Sens. Syst., 10, 127–134, 2021
https://doi.org/10.5194/jsss-10-127-2021
J. Sens. Sens. Syst., 10, 127–134, 2021
https://doi.org/10.5194/jsss-10-127-2021

Regular research article 01 Jun 2021

Regular research article | 01 Jun 2021

A classification technique of group objects by artificial neural networks using estimation of entropy on synthetic aperture radar images

Anton V. Kvasnov and Vyacheslav P. Shkodyrev Anton V. Kvasnov and Vyacheslav P. Shkodyrev
  • School of Cyberphysical Systems and Control, Peter the Great St. Petersburg Polytechnic University (SPbPU), St. Petersburg, 195251, Russia

Abstract. The article discusses the method for the classification of non-moving group objects for information received from unmanned aerial vehicles (UAVs) by synthetic aperture radar (SAR). A theoretical approach to analysis of group objects can be estimated by cross-entropy using a naive Bayesian classifier. The entropy of target spots on SAR images revaluates depending on the altitude and aspect angle of a UAV. The paper shows that classification of the target for three classes able to predict with fair accuracy P = 0,964 based on an artificial neural network. The study of results reveals an advantage compared with other radar recognition methods for a criterion of the constant false-alarm rate (PCFAR < 0.01). The reliability was confirmed by checking the initial data using principal component analysis.

Publisher's note: This article needs some licence clarifications. Therefore, the article is not available at the moment.

Publications Copernicus
Download

Please read the editorial note first before accessing the article

Short summary
We have prepared an article that demonstrates one of the ways to recognize objects on the ground surface. This paper is a result of experimental data that were collected with unnamed aerial vehicles (UAVs) with synthetic aperture radar. Although UAV radar has a small monitoring area, we noted that such pictures can contain the steady features of the mutual arrangement between detected objects. We have constructed an artificial neural network that solves the tasks of group object recognition.
Citation