Page 153 - ITU Journal Future and evolving technologies – Volume 2 (2021), Issue 2

ITU Journal on Future and Evolving Technologies, Volume 2 (2021), Issue 2

DOORS IN THE SKY: DETECTION, LOCALIZATION AND CLASSIFICATION OF AERIAL VEHICLES
USING LASER MESH

2
1
Wahab Khawaja , Ender Ozturk , Ismail Guvenc 3
1 Computer Systems Engineering Department, Mirpur University of Science and Technology, Mirpur AJK, Pakistan,
2,3 Electrical and Computer Engineering Department, North Carolina State University, Raleigh, NC.
NOTE: Corresponding author: Wahab Khawaja, wahab.ali@must.edu.pk

Abstract – Stealth technology and Unmanned Aerial Vehicles (UAVs) are expected to dominate current and future aerial
warfare. The radar systems at their maximum operating ranges, however, are not always able to detect stealth and small
UAVs mainly due to their small radar cross sections and/or low altitudes. In this paper, a novel technique as an alternative
to radar technology is proposed. The proposed approach is based on creating a mesh structure of laser beams initiated from
aerial platforms towards the ground. The laser mesh acts as a virtual net in the sky. Any aerial vehicle disrupting the path of
the laser beams are detected and subsequently localized and tracked. As an additional feature, steering of the beams can be
used for increased coverage and improved localization and classi ication performance. A database of different types of aerial
vehicles is created arti icially based on Gaussian distributions. The database is used to develop several Machine Learning
(ML) models using different algorithms to classify a target. Overall, we demonstrated through simulations that our proposed
model achieves simultaneous detection, classi ication, localization, and tracking of a target.

Keywords – Classi ication, detection, laser, localization, machine learning, mesh, radar cross section, stealth, tracking,
unmanned aerial vehicles (UAVs)

1. INTRODUCTION vehicle. There are also laser scanning techniques avail‑

able in the literature for the detection and tracking of

Unmanned Aerial Vehicles (UAVs) have applications in terrestrial moving objects [11, 12, 13]. Laser scanning

several areas nowadays [1], one of which is the defense
works on a similar principle to radars, i.e., relies on back‑
industry. The small size and ability to ly at low altitudes
scattered signals, and classi ies a moving target based on
make the UAVs practically invisible to conventional radar
individual laser scans at different instances of the time ob‑
systems [2] at long ranges. Moreover, stealth technol‑

tained from different parts of a target. Implementation

ogy is the most essential part of the current and future
of this technique is quite challenging, and there is lim‑

combat aerial vehicles. Stealth Aerial Vehicles (SAVs) can
ited amount of work available in the literature for the de‑
avoid being detected by radars due to their small Radar

tection of aerial targets using this technique. In [14], a
Cross Sections (RCS) that are achieved by using a mix of
laser‑based radar is used for the detection of UAVs. As the
techniques to absorb and scatter the incoming radar en‑
approach in [14] follows the basic radar principle, it also
ergy [3]. shares the disadvantages of the radar systems.
Radar technology has evolved signi icantly over the
decades. However, there are still known limitations of the Similar to radar systems, Electro‑

radar systems [4]. The basic radar principle still relies on Optical/Infrared (EO/IR) imaging is used for detection,

back‑scattered re lections from a potential target [5]. For tracking, and ication of aerial targets [15]. The

SAVs and UAVs, the back‑scattered re lections are weak operation of the EO/IR sensors are different from the

and the strength of the received signal is generally below radar systems. The EO/IR imaging uses ultraviolet,
the noise loor. Therefore, the target remains undetected visible and infrared spectral bands for different types of
by conventional radar systems over a signi icant distance, targets. The advantage of the EO/IR technique compared
i.e., insuf icient slant range. In the literature, there are to radars is that it can operate in the passive mode and
some radar systems proposed for detecting targets with the illumination is either provided by natural sources or

small RCS [6, 7, 8]. However, these radar systems are by the target itself. The ine details of the target iltered

too complex, expensive, and they are designed to use only from the background environment using EO/IR image

speci ic wavelengths that further contribute to complex‑ processing can help in the tracking, and classi ication

ity and high cost. of small and stealthy targets. However, the selection of

Different types of early warning radar systems can pro‑ the spectral band for EO/IR imaging is dependent on
vide speci ic detection capabilities against the SAVs and type of the target. The EO/IR imaging is also affected by

UAVs [9, 10]. However, the detection capabilities (i.e, RCS environmental and atmospheric conditions, e.g. haze,

as a function of detection range) vary with the operating fog, and clouds. The EO/IR imaging has a limited range

frequency of the radar system and the type of the aerial compared to radars. High resolution and sensitivity

EO/IR imaging is complex and expensive.
© International Telecommunication Union, 2021 139