International Journal of Transportation Science and Technology 5 (2016) 111–122

Contents lists available at ScienceDirect

International Journal of Transportation

Science and Technology
journal homepage: www.elsevier.com/locate/ijtst

Unmanned Aerial Aircraft Systems for transportation

engineering: Current practice and future challenges
Emmanouil N. Barmpounakis ⇑, Eleni I. Vlahogianni, John C. Golias
National Technical University of Athens, 5 Iroon Polytechniou Str, Zografou Campus, 157 73 Athens, Greece

a r t i c l e i n f o a b s t r a c t

Article history: Acquiring and processing video streams from static cameras has been proposed as one of
Received 11 November 2016 the most efficient tools for visualizing and gathering traffic information. With the latest
Received in revised form 24 January 2017 advances in technology and visual media, combined with the increased needs in dealing
Accepted 4 February 2017
with congestion more effectively and directly, the use of Unmanned Aerial Aircraft
Available online 10 February 2017
Systems (UAS) has emerged in the field of traffic engineering. In this paper, we review stud-
ies and applications that incorporate UAS in transportation research and practice with the
Keywords:
aim to set the grounds from the proper understanding and implementation of UAS related
Unmanned Aerial Vehicles
Traffic Engineering
surveillance systems in transportation and traffic engineering. The studies reviewed are
Traffic Monitoring categorized in different transportation engineering areas. Additional significant applica-
Surveillance tions from other research fields are also referenced to identify other promising applica-
Video Analytics tions. Finally, issues and emerging challenges in both a conceptual and methodological
level are revealed and discussed.
Ó 2017 Tongji University and Tongji University Press. Publishing Services by Elsevier B.V.
This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/
licenses/by-nc-nd/4.0/).

Contents

Introduction. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 112
Unmanned aerial vehicles for transportation and traffic engineering . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 113
A taxonomy of research applications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 113
Traffic monitoring . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 113
Logistics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 115
Road construction, photogrammetry and remote sensing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 116
Other applications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 116
Some conceptual, technical and algorithmic challenges. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 117
The size of problem and the type of the application . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 117
UAVs integration to cooperative networks and smart cities . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 119
Safety, security, privacy and legal concerns . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 119
Education and skills . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 120
Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 120
References . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 120

Peer review under responsibility of Tongji University and Tongji University Press.
⇑ Corresponding author. Fax: +30 210 772 1454.
E-mail addresses: manosbar@central.ntua.gr (E.N. Barmpounakis), elenivl@central.ntua.gr (E.I. Vlahogianni), igolias@central.ntua.gr (J.C. Golias).

http://dx.doi.org/10.1016/j.ijtst.2017.02.001
2046-0430/Ó 2017 Tongji University and Tongji University Press. Publishing Services by Elsevier B.V.
This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
112 E.N. Barmpounakis et al. / International Journal of Transportation Science and Technology 5 (2016) 111–122

Introduction

Traffic surveillance and monitoring has been one of the main tools for Transportation Managers and Engineers for years
and an integral part of traffic management and control strategies (Papageorgiou et al., 2008). Several algorithms or systems
have emerged to track moving object and analyse traffic, such as (Hsieh et al., 2006; Liu et al., 2008; Shukla and Saini, 2015;
Sivaraman and Trivedi, 2013). The visual perspective of the manner traffic (either vehicles or people) evolves over space and
time may assist the understanding of recurrent traffic conditions, the efficient management of pedestrian and vehicle traffic,
as well as the traffic and demand management under unexpected transportation network conditions (e.g. extreme conges-
tion, adverse weather conditions, riots, terrorist attacks), that may severely deteriorate the performance of the transporta-
tion networks and affect the security and safety of users.
Collecting visual information for large networks can be a challenging procedure. Installing stationary cameras to monitor
the extent of a transportation facility has been a successful practise for years. Nevertheless, several practical issues may
emerge; for example, there are cases where the area to be monitor is large and cannot be covered from static cameras. More-
over, installing stationary cameras and supplementary infrastructure can sometimes be too costly, especially when an area
does not need to be monitored anymore.
Even if the cost parameter from the problem of the transportation infrastructure monitoring could be alleviated, the prob-
lem of acquiring visual information and gathering data under the emergence of unexpected events is still not addressed. An
extreme event may occur at any place and any time. The response to such events should be made in a timely manner to
reduce their effects to the transportation system. Evidently, from an emergency response perspective, a setting of static cam-
eras fails to provide a clear picture of the unexpected extreme event, as the setting is specific usually with limited ability to
cover a transportation system (see Table 1).
Additionally, in rural environments, where problematic areas are more sparse, operators would sometimes have to deal
with large time intervals between identifying the situation, assessing all necessary steps and lastly taking measures to tackle
it, losing valuable time for safety and security and/or resources allocation. Therefore, some practitioners would use ground
vehicles as a supplement to the input coming from cameras along the network. Sometimes though, the area of interest may
not be accessed immediately, for example when a road accident causes heavy traffic jams upstream the arterial or when the
emergency area is not accessible. Similar conditions may arise in an urban setting, where dense road networks sometimes
add excessive delay for an emergency vehicle to reach its destination and provide first aid.
Until now, Manned Aerial Vehicles (MAV), usually helicopters operated by the police or air medical services, have been
the most appropriate means of providing live picture and information to the control centers and/or provide first aid in an
utmost situation. Except for the fact that – in principle - a MAV has high fixed and operation costs, there are many cases that
sending a helicopter with people inside or extremely costly equipment, over the area of interest is not always feasible, due to
high risk.
Recently, Unmanned Aerial Aircraft Systems (UAS) have been proposed as an alternative in order to overcome the above-
mentioned limitations and shortcomings of current practices. A UAS consists of three components: (1) the aircraft, which is
defined as an Unmanned Aerial Vehicle (UAV or drone); (2) communication and control; and (3) the pilot. This paper aims to
review research dedicated to using UAS in transportation and the advantages of airborne video as a means for acquiring high
quality naturalistic data for both practitioners and researchers. The structure of the paper is as follows. First, the advantages
of the UAS are described and their technical characteristics that can make them a game changer in Intelligent Transportation
Systems (ITS) infrastructure monitoring. Following, we describe some of the latest advances in their technological aspects
and important applications that UAVs have already been used for. Then, an analytical review of papers for airborne video
footage is conducted. Finally, some issues and challenges concerning UAVs safe and effective integration into ITS applications
are discussed.

Table 1
Comparison between static cameras, MAV and UAV.

Static cameras MAV UAV

Length coverage Low High High
Security/Privacy Medium Medium Low
Cost (acquiring and maintenance) Low High Low
Multiple uses Low High High
Energy efficiency Low Low High
Deployment Low High Low
Operational time High High Low
Operation under adverse weather Medium Low Low
Risk Low High Medium
Endurance High High Low
Video post-processing skills Medium High High
Data transfer, communication and storage Low High High
Operation skills Low High Medium
Training requirement Low High Medium
Complexity Medium High Medium
 E.N. Barmpounakis et al. / International Journal of Transportation Science and Technology 5 (2016) 111–122 113

Fig. 1. A fixed-winged UAV A fixed-wing UAV (left) (Aerial Data Systems, 2016) and a rotary wing UAV (right) (DJI, 2016).

Unmanned aerial vehicles for transportation and traffic engineering

A UAV or drone is any aircraft, which is not operated by a pilot on-board. This means that the aircraft is controlled either
by a pilot on the ground or by electronic systems (semi or fully autonomously). UAVs can be further categorized by the type
of their wings to fixed-wing aircrafts, that use wings to generate the lift because of forward airspeed, and rotary wing air-
crafts, that use (rotor) wings revolving around a single axis to generate the lift (Fig. 1). Although UAVs were firstly introduced
for military missions, their use has been recently expanded to civil applications; the last was facilitated by the a burst in the
UAV industry which systematically provides smaller and lower cost aircrafts (Mahadevan, 2010).
A significant part of the civil applications is focused on aerial photography (Cheng, 2015). Lately, UAVs have found appli-
cations in many areas (agriculture, search and rescue missions, infrastructure inspection), especially with the latest advances
in their technology and the related sensor technologies (Budiyono, 2008). For transportation engineers, UAS have been intro-
duced as a novel and cost-effective ‘‘eye-in-the-sky” solution mainly to collect massive trajectory data from road arterials
and replace the old approach of using already pre-installed cameras.
Most UAVs can be on air in a matter of minutes and, with the latest advances in their lightweight materials and equip-
ment, they can cover large distances in very short time intervals, while most of the UAVs use eco-friendlier energy sources
(for detailed description of UAV types, technical specifications etc. see the review in Gupta et al. (2013)). In addition, since a
UAV can be programmed to fly automatically to a specific area, it could reach the specific area of interest more rapidly since
it takes less time to be on air than a MAV. The fact that no crew is required onboard makes it optimal for emergency evac-
uation situations (e.g. small or large scale evacuations) or high-risk situations (e.g. terrorist attacks), where no more lives are
put in danger. Moreover, their comparatively smaller size, they can reach inaccessible places for a MAV, for example a dense
urban area with tall buildings and other transportation infrastructure. The advantage of their small size is also crucial when
it comes to gathering naturalistic data over a road arterial. Although this may raise some privacy issues that will be analyzed
in a later paragraph, UAVs offer a more non-intrusive way of recording traffic phenomena (Barmpounakis et al., 2016).
While each type of UAV (rotary or fixed wings) have distinct advantages over the other, both of them may offer a top view
of a road arterial or an intersection, and issues like hidden views, difficult viewing angles and limited length can be more
easily resolved. When it comes to rotary-wing UAVs, they are most of the times more versatile, being able to land in limited
spaces or maneuver to provide the ideal picture to the operating center. An important asset is that most commercial rotor-
crafts are equipped with high definition cameras and combined with their hovering abilities, researchers have the potential
to acquire high quality traffic data. As it can easily be understood, the aerial view of a UAS could provide useful insights to
researchers, while they could be of crucial importance in emergency response situations, for example UAVs that provide a
rapid first aid during an utmost incident.

A taxonomy of research applications

Tables 2–4 summarize the existing literature related to ITS applications and UAVs with respect to the research area, the
exact type of application and the type of aircraft that was utilized. In the following sections, the UAV related literature in
transportation and traffic engineering is further analyzed.

Traffic monitoring

An interesting review on the subject focusing on advantages and disadvantages of each method can be found in Kanistras
et al. (2014). In this review, applications on traffic monitoring are organized thematically identifying where research has
gone thus far. At first, research on UAVs aimed to identify their potential in general applications mostly on monitoring vehi-
cles. One of the first project that was dedicated to the development of a fully autonomous UAV was the WITAS Project
(Doherty et al., 2000; Granlund et al., 2000; Heintz et al., 2007). This UAV was designed to be capable to navigate at different
altitudes and conduct several activities, such as identifying, tracking and monitoring specific vehicles. Mirchandani et al. dis-
cussed the potential of collecting traffic data from aerial video footage; several parameters were able to be extracted, such as
densities, travel times, turning counts, queue lengths etc. (Mirchandani et al., 2002). In Shastry and Schowengerdt (2002),
114 E.N. Barmpounakis et al. / International Journal of Transportation Science and Technology 5 (2016) 111–122

Table 2
Summary of research studies on UAV applications to traffic management.

Author Year Type Aim of the study Research highlights

Doherty et al. 2000 UAV Identify, track and monitor vehicles (WITAS Project) A complete concept of deploying UAV for
road and traffic applications
Granlund et al. 2000 UAV Identify, track and monitor vehicles (WITAS Project) Computer vision issues
Mirchandani et al. 2002 MAV Extract kinematic parameters like densities, travel times, Identify UAVs’ potential for traffic flow
turning counts etc. monitoring and management
Shastry and 2002 MAV Stabilize video and track vehicles Combination of GIS and airborne video
Schowengerdt
Frew et al. 2004 UAV Track the roadway (UC Berkeley) Accuracy issues due to aircraft altitude
Srinivasan et al. 2004 - Examine feasibility of using UAVs for transport surveillance Identify UAVs’ potential as a tool for DOTs
(Florida DOT)
PB Farradyne 2005 - Examine feasibility of using UAVs as part of ITS infrastructure. Identify UAVs’ potential as a tool for DOTs
Kaaniche et al. 2005 UAV Follow road and detect moving vehicles Effective, fast and real-time detection
algorithm
Coifman et al. 2006 UAV Extract traffic parameters like LOS, AADT, intersections Aerial video footage potential for
operating conditions, OD tables etc. transportation applications
Lin et al. 2006 - Concept and first approach on transforming real time data to Aerial video footage potential for
traffic information transportation applications
Reinartz et al. 2006 MAV Automatic vehicle detection and measure velocity Aerial video footage potential for
transportation applications
Heintz et al. 2007 UAV Identify, track and monitor vehicles (WITAS Project) Real time tracking
Puri et al. 2007 UAV Use real time traffic data as input to simulation models. Swarm of UAVs’ potential identified.
Ro et al. 2007 UAV Examine feasibility of using UAVs as part of ITS infrastructure. Next research steps
Yu Min Chen and 2007 UAV Test quality connection with a DOT (Michigan DOT) Security and connectivity issues.
Oh
Lenhart et al. 2008 - Automatic way of monitoring traffic with vehicle detection. Use of sequential images
Li 2008 UAV Detect vehicles for traffic flow computation and vehicle Effective fuzzy algorithm
classification.
McCormack and 2008 UAV Examine feasibility of using UAVs for transport surveillance Identify UAVs’ potential as a tool for DOTs
Trepanier
Cheng et al. 2009 UAV Detect and track vehicles in real-time video Efficient and effective algorithm
Braut et al. 2012 UAV Estimating OD matrices at complex intersections Identifying video issues for vehicle detection
Liu et al. 2013 UAV Optimization model for UAV route planning. Identify issues for UAV as a mean of
collecting traffic information
Salvo et al. 2013 UAV Measure gap acceptance Proof of reliability of UAVs
Zhang et al. 2013 UAV Identify traffic incidents, for example stopped vehicles, vehicles High accuracy in incident detection
moving the wrong way etc.
Gao et al. 2014 UAV Automatically identify vehicular trajectories and measure High accuracy in automatic vehicle
speeds and accelerations. detection
Kanistras et al. 2014 - Review on application for traffic monitoring UAVs’ potential and advantages for traffic
monitoring
Lima et al. 2014 MAV Automatically tracking vehicles High accuracy in trajectory extraction
Salvo et al. 2014a UAV Macroscopic models comparison using airborne video data Advantages of UAVs in monitoring traffic
Salvo et al. 2014b UAV Compare speed data between GPS and UAV High accuracy and minimum number of
points for calibration
Wang et al. 2014 UAV Collect vehicle trajectory data Accuracy affected by altitude.
Xin et al. 2014 UAV Compare speed data between ground radars and UAV Detailed description of tracking and speed
estimation procedure
Zhang et al. 2014 UAV Detect road boundaries. High Accuracy in road boundary detection.
Gheisari et al. 2015 - Suggestions on using UAS as part of ITS infrastructure. Interviews conducted with DOT personnel.
Lee et al. 2015 UAV Traffic and roadway incident monitoring. The quality of video footage affects UAS’
effectiveness.
Liu et al. 2015 UAV Identify stopped vehicles Simulation and flight experiment conducted
Wang et al. 2015 UAV Detect and track vehicles High accuracy in vehicle detection and
tracking
Barmpounakis 2016 UAV Extract kinematic parameters like speeds, acceleration and High accuracy and step-by-step description
et al. trajectories.
Erdelj and 2016 - Review of main disaster management applications Detailed review of UAV-assisted
Natalizio applications and open issues

authors describe a method to simultaneously stabilize the aerial video footage and track vehicles. In Srinivasan et al. (2004),
the feasibility of using UAVs for transport surveillance was examined. Moreover, simulation test experiments took place aim-
ing mostly at connectivity, network issues, video streaming and signal strength issues. Frew et al. implemented a UAV and
vision-based techniques in order to track the roadway with over 90% accuracy in images of real roads (Frew et al., 2004). In
PB Farradyne (2005) a different study is conducted, in which a concept of UAV operations as part of the ITS infrastructure is
described, and although no flights were conducted, the feasibility of such ideas and the need for further developments of
airborne video footage is identified. In Yu Min Chen and Oh (2007) an experiment took place to test the quality of the
 E.N. Barmpounakis et al. / International Journal of Transportation Science and Technology 5 (2016) 111–122 115

connection between a UAV and the monitoring terminals of the Michigan Department of Transportation, although security
concerns are identified. Ro et al. (2007)) tested the applicability of sUAV systems for highway traffic monitoring and con-
cluded that UAVs can be a significant part of the ITS infrastructure. In McCormack and Trepanier (2008) the potential of
UAV as part of a Department of Transportation is identified, while several concerns on safety and privacy issues are reported.
With the advances in UAV technology and materials, several other studies were conducted, with some of them focusing in
microscopic data and more specific phenomena, like detailed trajectory extraction and microscopic traffic parameters calcu-
lation. In Kaaniche et al. (2005) a vision system is described, where the UAV can follow a specific part of a road arterial and
identify moving vehicles. Reinartz et al. were able to achieve 3 km/h velocity accuracy from airborne cameras and automatic
vehicle detections (Reinartz et al., 2006). Although, a UAV was not included in the specific research, the importance of air-
borne data is identified for standard instrumentation, for analysis of traffic flow and for input into traffic models and sim-
ulations. In Coifman et al. (2006) using data from a UAV flying in urban environment several empirical tasks were
completed, for example determining level of service (LOS), estimating average annual daily travel (AADT), measuring inter-
sections operating conditions and creating origin destination flows. Some preliminary results to convert video data to traffic
information were produced in Lin et al. (2006), while in Puri et al. (2007) real-time visual data were collected as inputs to
improve existing traffic simulation models, using statistical profiles from UAV video footage. In the latter, the authors con-
clude that if multiple UAV can be used above specific intersections, significant information can be extracted.
Recent studies have focused on the post processing of the aerial video using advanced modeling and machine learning for
extracting traffic information. In Li (2008) an approach using fuzzy image segmentation for vehicle detection is described,
information that could be used for traffic flow computation or vehicle classification. In Lenhart et al. (2008) an automatic
way of monitoring traffic is tested with high accuracy in vehicle detection. In Cheng et al. (2009) a fixed wing UAV is used
to detect and track vehicles using real-time video data processing algorithms.
Lately, real-time information from UAVs has been in the center of attention, with several emerging issues in communi-
cation, data accuracy and video processing. In Braut et al. (2012) origin destination (OD) matrices are estimated while the
authors emphasize the need for further research steps in the stabilization procedure for better accuracy and matching vehi-
cles between frames. In Liu et al. (2013) an optimization model is described which aims to plan UAV routes in order to mon-
itor road segments. However, although the algorithms show quite good results, the authors conclude on several issues that
need to be tackled first, for example real time video stabilization. In Zhang et al. (2013) authors used a UAV in order to iden-
tify specific traffic incidents, for example vehicles moving in the wrong way or stopped vehicles with 100% and 96.4% detec-
tion rate respectively. The gap acceptance of drivers is examined in Salvo et al. (2013) where data was collected through
UAV-based video footage while in Salvo et al. (2014a)) authors dealt with macroscopic models comparison using airborne
video data. In Gao et al. (2014) a low cost quadcopter was used to automatically identify vehicular trajectories while veloc-
ities and acceleration are also collected. In Zhang et al. (2014) used a UAV in order to detect road boundaries using multiple
sources of information. In Lima et al. (2014) a similar system is described for automatic vehicle tracking and, although a UAV
was not used at the specific research, the authors conclude that using one could enhance the accuracy and detectability of
the algorithms. In Salvo et al. (2014b), authors compared speed data that were acquired via GPS and UAV video footage data,
with the results showing small deviations between the two measurements. A similar research in Xin et al. (2014) compared
vehicle speeds that were acquired from UAV with speed measurements from ground radars, with over 90% accuracy. In
Wang et al. (2014) propose a low cost system to collect vehicle trajectory data with 10 cm accuracy. In Lee et al. (2015)
the authors examined the applicability of UAV for traffic and roadway incident monitoring. In this research, commercial
4G networks were used for video transmission to a ground station, while the need for video stabilization is also reported.
In Liu et al. (2015) a simulation and an experiment for detecting stopped vehicles along low-volume roads was examined,
while several limitations are also identified such as adverse weather conditions and video stability. In Wang et al. (2015) a
method to detect and track vehicles is described with experiments showing an error rate lower than 3.9% in detecting and
2.1% in tracking vehicles. In Gheisari et al. (2015) several uses of UAVs are proposed in traffic management, transportation
and construction disciplines as resulted after a number of interviews with personnel from the Georgia Department of
Transportation. In Barmpounakis et al. (2016) a method for extracting trajectories from moving objects is described with
maximum error in speed estimation being less than 1 km/h.

Logistics

One of the areas that UAVs will be extensively applicable in the near feature is logistics. The potential use of UAS in logis-
tics has been first researched in non-civil applications (McCoy, 2003; Milgram et al., 2003). UAS can be a quite cost effective
solution for package deliveries in civil applications (Raffaelle, 2014). However, not many studies have implemented practical
applications in this area since several challenges need to be addressed, with the most critical being: i. vehicle design (mate-
rials and payload), ii. localization and navigation (finding the appropriate route), and iii. vehicle coordination (massive num-
ber of UAVs delivering goods). Such a problem is discussed in Murray and Chu (2015) for delivering parcels around an urban
setting.
Some ideas concerning logistics using unmanned robots, not only aerial but ground and underwater drones, are also
reported in Bujak et al. (2011), in which authors also emphasize the use of UAV for traffic coordination. A different study
underlined that UAV implementation instead of land vehicles in vaccine transportation would increase vaccine availability
and decrease in costs (Haidari et al., 2016). In Cage (2016) UAS were tested to deliver goods on tankers.
116 E.N. Barmpounakis et al. / International Journal of Transportation Science and Technology 5 (2016) 111–122

Table 3
Summary of research studies on UAV applications to logistics.

Author Year Type Aim of the study Research Highlights

McCoy 2003 - Examine the potential of using UAV for the US army Identifying UAVs’ potential
Milgram 2003 – Autonomous glider system for delivering purposes Compared different types for delivering purposes
et al.
Bujak et al. 2011 – Examine the potential of using unmanned vehicles for Emphasize telematics solutions for future logistic
logistic purposes applications
Raffaelle 2014 – Examine the potential of using UAV for logistics Identify issues and additional challenges
Murray and 2015 - Optimal routing and scheduling of UAV Minimizing time required for delivering
Chu
Haidari et al. 2016 UAV Use UAV for vaccine transportation UAV systems can increase vaccine availability and
decrease costs
Cage 2016 UAV Delivering goods on tankers (Maersk Group) Focus on safety

Road construction, photogrammetry and remote sensing

UAVs’ potential has also been identified in Photogrammetry and Remote Sensing. Although the aim of this review is to
focus on UAVs applications for Transportation purposes, the reader if interested can find important literature and historic
background in the following reviews (Colomina and Molina, 2014; Eisenbeiss, 2004; Watts et al., 2012).
Another interesting study can be found (Siebert and Teizer, 2014) with several applications like landfill survey, road con-
struction, high-speed rail construction and a spoil site project. In (Ma et al., 2013) several applications for urban constructors
and planners are described, like serve city lay-out, guide the development demolition, calculate the percentage of greenery
coverage among others. In Dobson et al. (2013) and (Knyaz and Chibunichev (2016) methods to analyze road surface using
3D models are described. A series of research on road condition assessment can be found in (Zhang, 2006; Zhang and
Elaksher, 2012) with results reaching accuracy to 0.50 cm. In Díaz-Vilariño et al. (2016) the applicability of UAVs in studying
road runoff, especially on mountain roads.

Table 4
Summary of research studies on UAV applications to Road Construction, Photogrammetry and Remote Sensing.

Author Year Type Aim of the study Research highlights

Eisenbeiss 2004 UAV Photogrammetric flight over an ancient Helicopters advantages and current issues
settlement
Zhang 2006 UAV Photogrammetric mapping system for road UAVs’ potential in road condition will be further increased using 3D
condition assessment models
Watts et al. 2012 - Advantages of each UAV type for remote Current state of regulations depending on UAV type
sensing applications
Zhang and 2012 UAV Measuring unpaved road surface distresses UAV are feasible for collecting high accuracy road surface condition
Elaksher data
Ma et al. 2013 UAV Using UAV for Urban Construction and Special requirements of photogrammetry or classification
Planning
Dobson et al. 2013 UAV Unpaved road assessment Easily transported and deployable to create 3D road surface models
Colomina and 2014 - Review of UAV for photogrammetry and Potential of UAS is identified and the need for additional research and
Molina remote sensing technology is referred
Siebert and 2014 UAV Several photogrammetric applications Factors and errors influencing UAV- based photogrammetric
Teizer using UAV measurements were defined and discussed
Knyaz and 2016 UAV Automated road surface reconstruction UAS’ potential in road condition is studied
Chibunichev
Díaz-Vilariño 2016 UAV Using UAV for evaluation of road runoff High accuracy achieved and comparison to LiDAR systems
et al.

Other applications

As seen above, UAVs’ unique characteristics can find application in many aspects of everyday life. Below, some applica-
tions are referenced to see through UAVs’ possibilities and capabilities in a clearer way (Table 5). In Merino et al. (2005) a
system which incorporates a cooperative fleet of UAVs for fire detection is described. Except for the cooperative actions
between UAVs that are described in the specific study, a UAS which is equipped with cameras and other sensors is presented
to detect and localize fires with computer vision techniques. A bridge inspection system using UAVs is described in Metni
and Hamel (2007) using a UAV with a video camera. Ιn Linchant et al. (2015) a review is conducted to examine whether UAVs
have a potential in wildlife monitoring or in Freeman and Freeland (2014) where authors examine UAV operations for agri-
culture. It should be noted however that in both studies several arguments are raised concerning legislation and safety con-
 E.N. Barmpounakis et al. / International Journal of Transportation Science and Technology 5 (2016) 111–122 117

cerns. Finally, a review on emerging application possibilities including several environmental aspects can be found in Beloev
(2016).
A vivid research filed for UAVs is disaster management and assessment. In Ezequiel et al. (2014) authors used the com-
bination of aerial surveying, ground observations and collaborative sharing with experts for disaster estimation after
Typhoon Haiyan in the Philippines. Similarly, Maza et al. (2011) describe an architecture of a multi UAV system that con-
tribute in disaster management and other applications through cooperation and coordination. Finally, in Erdelj and
Natalizio (2016) the uses of UAVs for disaster management are reviewed, including disaster information fusion applications
or establishing standalone communication systems.

Table 5
Summary of research studies on UAV applications to infrastructure inspection, extreme events detection and environment monitoring.

Author Year Type Aim of the study Research Highlights

Merino et al. 2005 UAV Using cooperative UAV for Fire detection Algorithms for fire detection and cooperative actions
Metni and 2007 UAV Bridge inspection system Method for limiting UAVs’ orientation
Hamel
Maza et al. 2011 UAV Cooperative UAV for Disaster Management In the future, the cooperation of manned and
unmanned aerial vehicles will be required
Freeman and 2014 – UAV operations for agriculture There is momentum toward UAS deployment in
Freeland agriculture
Ezequiel et al. 2014 UAV UAV for post-disaster assessment, environmental UAV aerial imagery provides data essential for analysis
management and infrastructure development and effective action
Linchant 2015 – Review the potential in wildlife monitoring Advantages and issues for UAS monitoring wildlife
et al.
Beloev 2016 – Review on emerging application possibilities with several Overview of the most interesting and widely available
environmental aspects applications

Some conceptual, technical and algorithmic challenges

The previous section revealed the great potential UAV can have as part of ITS infrastructure in several aspects of trans-
portation engineering (Barmpounakis et al., 2016; Coifman et al., 2006; PB Farradyne, 2005; Gheisari et al., 2015; Kanistras
et al., 2014; McCormack and Trepanier, 2008; Reinartz et al., 2006; Salvo et al., 2014a; Srinivasan et al., 2004). From the anal-
ysis of literature, it is evident that their capabilities can extend the available tools of researchers, operators and managers.
Moreover, it is evident that there exist several influential factors that may lead a research or a practitioner towards choosing
between static and aerial camera settings. Fig. 2 describes the sequential decision making process from the problem state-
ment to the operational aspect of the application (backend or real-time processing) and the factors that may lead to the use
of UAVs for video recording.
Taking a systematic look at the documented use of UAVs in transportation applications, several reported issues that may
affect the operability of UAS in commercial activities have been reported. For example, in Finn and Wright (2012) the authors
conclude that the use of UAVs raises many issues concerning as a ‘‘surveillance system” and, due to the different practition-
ers, types and capabilities of UAVs, a multi-layered regulatory mechanism is suggested to fully address current regulations.
Apart from the technical challenges, which fall beyond the scope of this paper, such as how to increase the flight time by
using optimum materials, or new battery technologies, there are some emerging challenges that deserve further discussion.

The size of problem and the type of the application

Most transportation problems extend both temporally and spatially, whereas, at their emergence, they can be signifi-
cantly localized, especially in cases of extreme events and disasters. Taken that the UAVs have an inherent flight time con-
straint, their use in large-scale transportation problems should be consistently designed and executed. Such a concept would
require either advanced tech UAVs, or group (swarm) of UAVs to expand their capabilities. as described in Ordoukhanian and
Madni (2016). The use of multiple UAVs comes with multiple other issues to consider, such as system’s resilience, complex-
ity and communication between the UAVs (Ordoukhanian and Madni, 2016).
Regarding the type of the application, it is evident that others may requires solely to have ‘‘eyes in the sky”
(Barmpounakis et al., 2016; Heintz et al., 2007; Kanistras et al., 2014; Lin et al., 2006), for example image and video during
disasters, or evacuation of large transportation infrastructures, and others that are based on quantifications from video foo-
tages (e.g. queue lengths during congested periods, incident effects to traffic (Coifman et al., 2006) etc.). The latter is much
more difficult to tackle as it requires that the gathered data are stored either locally (on the UAV) or on an external server. In
case where real-time computations are taking place, the problem becomes much more complex, as transferring, storing and
processing data should be conducted real-time. In such as case, for computational reasons, reduced data capturing resolu-
tions should be considered that may significantly affect the accuracy of the analyses (Yu Min Chen and Oh, 2007).
118 E.N. Barmpounakis et al. / International Journal of Transportation Science and Technology 5 (2016) 111–122

Fig. 2. Decision parameters for video recording mode choice.

Taking a deeper look at managing UAV real-time information, except for the security issues, several other topics should be
examined concerning the optimization procedure on data size and transfer time (Yu Min Chen and Oh, 2007). In the same
context, findings indicate that taking advantage of the visual information from aerial footage is most of the times available
only after time consuming processing. Therefore, the design of real-time and effective stabilization algorithms, which is the
main time consuming post-production procedure, can extend the efficiency and potential of UAS (Aguilar and Angulo, 2014a,
2014b; Knoppers et al., 2012).
Literature has emphasized the need for developing computer vision techniques that can assist GPS-based navigation of
UAVs, especially in densely populated areas where GPS signal is not reliable or sufficient, e.g. when signal dropouts occur
(which usually happens in urban areas, when flying through terrestrial urban canyons or when operating on remote plan-
etary bodies) (Campoy et al., 2009). It should be noted however, that real time calculations and estimations may affect the
 E.N. Barmpounakis et al. / International Journal of Transportation Science and Technology 5 (2016) 111–122 119

energy efficiency of UAVs, by using additional on-board hardware either for computations (processing and saving data) or for
transmitting bigger data packages. As seen previously, one of the main problems that need to be overcome when dealing
with aerial video footage is the video stabilization procedure. Although, special equipment, for example gimbals, are used
as a first step stabilization process in most commercial UAS, they can reduce only rough bias. For high quality data and
improved calibration, a second step stabilization process is required. In Knoppers et al. (2012) the authors describe a system
that can stabilize airborne video with high performance and underline the difficulties in stabilizing the video in real-time. In
a series of studies authors focus on video stabilization that can be used in real time video footage, which would be of crucial
importance in extracting kinematic characteristics while the UAV is on the air (Aguilar and Angulo, 2014a, 2014b).
In Jiang and Cao (2016) an algorithm for detecting and tracking vehicle with adequate accuracy is described; authors
report several shortcomings, for example tracking parked vehicles, shakiness of the camera, distinguishing moving vehicles
with similar color to the background etc. In Rodriguez-Canosa et al. (2012) and Su et al. (2014) algorithms and system for real
time detection and tracking systems of moving objects are described. In a different research, another algorithm for automatic
road detection is described in Zhou et al. (2015a) with two different experiments taking place to demonstrate its efficiency.

UAVs integration to cooperative networks and smart cities

One of the areas that UAVs have a great potential in contributing with their involvement is the concept of smart cities
(Mohammed et al., 2014). With the latest advances in big data and Internet of Things (IoT), researchers have also referred
to the previously mentioned concept of swarm of UAVs (Wu et al., 2016) to use it for urban sensing around the city. However,
it should be noted that except from the technical issues that this approach may rise (for example, collision avoidance sys-
tems, navigation etc.) the way this system of UAVs collaborates and becomes an effective means of collecting accurate and
massive information is a complex optimization problem. In a different study, the business and technical challenges that face
UAV applications’ development and project management are addressed (Idries et al., 2015). In Chow (2016), a real-time
approach for UAV dynamic routing is proposed. In Carnie et al. (2006) algorithms for ‘‘sense and avoid” technology were
developed and although the specific study does not refer to civilian UAS, the necessity for such a technology is referred
as a prerequisite for civilian use. A more recent study on sense and avoid systems can be found in Sapkota et al. (2016).
In Zhao and Pei (2012) a vision-based algorithm is described that can be used for automatic landing systems for UAVs.
Others dealt with the energy efficiency of a UAS using a Game Theoretic approach (Abdulla et al., 2015). In the same con-
text of smart cities and IoT, UAVs are also a promising tool for creating mobile ad-hoc networks when during emergency
situations existing infrastructure fails, or when there is a need for excessive coverage, or due to urban environment’s obsta-
cles that may affect existing communication quality (Namuduri et al., 2013). Similarly, in Zhou et al. (2015b) potential
research issues and challenges of aerial-ground cooperative networks using multi-UAV systems are discussed.

Safety, security, privacy and legal concerns

Privacy issues mainly have to do with sensitive data of people caught in video footage or inaccessible places
(Barmpounakis et al., 2016). However, privacy issues may also refer to network security. The wireless transmission of sen-
sitive data over the air could also raise concerns for possible cyber-attacks or other illegal actions, especially when these data
affect public security and operations (Sbeiti et al., 2016). As far as flights over restricted areas are concerned, some police
forces have proposed the use of trained eagles as an anti-drone tool (IEEE Spectrum, 2016).
Another important issue to be considered are flights over people, property or unpermitted areas (Ro et al., 2007). One
would argue that current UAV technology offers several protective measures, for example UAV parachutes that are automat-
ically deployed when it detects that something has gone wrong or other failsafe systems that use automatic navigation to
return back to its base. However, not all systems are equipped with such protective tools while their reliability is still ques-
tionable. Moreover, since most small UAV are sensitive to weather conditions, that sometimes change rapidly, it should be
very clear for operators whether a safe flight can be conducted or not. In addition, other important questions that need to be
addressed are whether UAVs would be allowed to fly close to airports or airways, putting an immediate danger to manned
aircrafts and what the allowed maximum flight altitude should be. For example, while safety is a first priority issue, one
should take into account that for better spatial accuracy a UAV should be flown in a lower altitude. For all the above men-
tioned issues, both the Federal Aviation Administration (FAA) (Federal Aviation Administration, 2016) and the European Avi-
ation Safety Agency (EASA) (European Aviation Safety Agency, 2016) have published regulations concerning UAV civil
operations where most of those issues are clearly covered and defined. However, since these rules are still new and have
not yet clearly been applied, and only by practising will it be possible to unveil possible weaknesses and ambiguities.
Finally, although some UAS can execute automated flights, current regulations require from the UAV operator or another
observer always to maintain visual contact. In an urban setting, however, where tall buildings are present most of the times,
this may complicate operations and therefore their effectiveness. Similarly, if a system of UAVs is monitoring a specific area,
their flight paths should be accurately defined, avoiding tall infrastructure and other obstacles that may be found in such an
environment. In Mccarley and Wickens (2004) some additional human factors concerning the UAV use are discussed and
categorized by (i) displays and controls, (ii) Automation and System Failures, (iii) Crew Composition, Coordination, Selection
and Training.
120 E.N. Barmpounakis et al. / International Journal of Transportation Science and Technology 5 (2016) 111–122

Education and skills

The emergence of novel and advanced technological solutions to gather and analyse transportation data often drives the
need to test and evaluate new modeling paradigms robust to big data, imperfections and real-time computations, but also to
design and operate applications, which require an advanced technological background. For transportation engineers, specific
information technology (IT) skills should be developed for the full integration of UAS in the transportation section. Although,
a Transportation engineer, practitioner or researcher, may never fly a UAV himself, in case they are part of a specific ITS
infrastructure, definite and clear communication between all involved parts is necessary for safety.
The above skills are not only linked to UAV usage, but is a generalized requirement of future transportation science and
practice. Currently, the landscape of ITS applications is dominated by tasks such as efficient data aggregation, verification
algorithms, Computational Intelligence and machine learning for optimization, massive data mining and predictive analytics
(Ali et al., 2012; Vlahogianni, 2015). The era of big data and the changing transportation landscape will drive the need to
develop new educational paradigms to enhance the skills of future transportation engineers (Vlahogianni and
Barmpounakis, 2017).

Conclusion

UAVs have recently emerged as a viable alternative to tackle problems on visual monitoring an improve its use to trans-
portation applications. In this paper, a taxonomy and a critical overview of research applications on UAV has been conducted
with emphasis to applications to (1) traffic monitoring; (2) freight delivery; (3) road construction; (4) photogrammetry and
remote sensing. Following, the emerging challenges from using UAVs in transportation problems have been discussed. The
discussed challenges related to the size of problem and the type of the application, UAVs integration to cooperative networks
and smart cities, issues of safety, security, privacy and legal concerns, as well as issues related to education and skills.
The extensive literature review highlighted several possible UAV applications to transportation research and practice.
Compared to existing tools UAS are a promising tool of the ITS infrastructure to enhance part of the operations of traffic mon-
itoring and managing. Apart from the ongoing debate on regulations and safety measures, the present paper underlined sev-
eral technical issues that should be tackled for UAVs to be an efficient equipment for transportation engineers.
From the analysis of literature, it is evident that the future of the use of UAV to transportation will be dominated by
advanced algorithms and tools to ensure:

 the safe and effective navigation of UAV above transportation infrastructure

 their energy efficient use
 the mining of critical information based on the predictive analytics

The use of computer vision techniques and remote sensing information (such as photogrammetric applications or road
construction and maintenance), for processing the aerial video footage are the cornerstone of success. Evidently, security,
privacy and legislation issues are due to concern legislators and regulators in the near future, when UAV start to be deployed
around above us. Yet, the technical limitations, as well as when and how they will be overcome will set the pace of advances.

References

Abdulla, A.E.A.A., Fadlullah, Z.M., Nishiyama, H., Kato, N., Ono, F., Miura, R., 2015. Toward fair maximization of energy efficiency in multiple UAS-Aided
networks: a game-theoretic methodology. IEEE Trans. Wirel. Commun. 14, 305–316. http://dx.doi.org/10.1109/TWC.2014.2343219.
Aerial Data Systems, 2016. Fixed-Wing UAV [WWW Document]. URL <http://aerialdatasystems.com/fixed-wing/>.
Aguilar, W.G., Angulo, C., 2014a. Optimization of robust video stabilization based on motion intention for micro aerial vehicles. Syst. Signals Devices (SSD),
Int. Multi-Conference Accepted. doi:10.1109/SSD.2014.6808863.
Aguilar, W.G., Angulo, C., 2014b. Real-time video stabilization without phantom movements for micro aerial vehicles. EURASIP J. Image Video Process. 2014,
46. http://dx.doi.org/10.1186/1687-5281-2014-46.
Ali, K., Al-Yaseen, D., Ejaz, A., Javed, T., Hassanein, H.S., 2012. CrowdITS: Crowdsourcing in intelligent transportation systems. IEEE Wirel. Commun. Netw.
Conf. WCNC 3307–3311. http://dx.doi.org/10.1109/WCNC.2012.6214379.
Barmpounakis, E.N., Vlahogianni, E.I., Golias, J.C., 2016. Extracting kinematic characteristics from unmanned aerial vehicles. Transp. Res. Board 95th Annu.
Meet. Compend. Pap. 16, p. 16.
Beloev, I.H., 2016. A review on current and emerging application possibilities for unmanned aerial vehicles. Acta Technol. Agric. 19, 70–76. http://dx.doi.org/
10.1515/ata-2016-0015.
Braut, V., Culjak, M., Vukotic, V., Segvic, S., Sevrovic, M., Gold, H., 2012. Estimating OD matrices at intersections in airborne video – a pilot study. MIPRO,
2012. Proc. 35th Int. Conv., pp. 977–982.
Budiyono, A., 2008. Advances in unmanned aerial vehicles technologies. Int. Symp. Intell. Unmanned Syst. ISIUS2008, Nanjing, China.
Bujak, A., Smolarek, M., Ge˛bczyńska, A., Gȩbczyńska, A., Ge˛bczyńska, A., 2011. Applying military telematic solutions for logistics purposes. Mod. Transp.
Telemat. 239 CCIS, pp. 248–256. doi:10.1007/978-3-642-24660-9_29.
Cage, S., 2016. Flown out by drone [WWW Document]. Maersk Tankers. <http://www.maersk.com/en/hardware/2016/03/flown-out-by-drone> (accessed
3.30.16).
Campoy, P., Correa, J.F., Mondragón, I., Martínez, C., Olivares, M., Mejías, L., Artieda, J., 2009. Computer vision onboard UAVs for civilian tasks. J. Intell. Robot.
Syst. Theory Appl. 54, 105–135. http://dx.doi.org/10.1007/s10846-008-9256-z.
Carnie, R., Walker, R., Corke, P., 2006. Image processing algorithms for UAV ‘‘sense and avoid.” Proc. 2006 IEEE Int. Conf. Robot. Autom. 2006, ICRA, pp. 2848–
2853. doi:10.1109/ROBOT.2006.1642133.
Cheng, E., 2015. Aerial Photography and Videography Using Drones. Peachpit Press, San Francisco, CA.
 E.N. Barmpounakis et al. / International Journal of Transportation Science and Technology 5 (2016) 111–122 121

Cheng, P., Zhou, G., Zheng, Z., 2009. Detecting and counting vehicles from small low-cost UAV images. ASPRS 2009 Annual Conference, Baltimore, pp. 138–
144.
Chow, J.Y.J., 2016. Dynamic UAV-based traffic monitoring under uncertainty as a stochastic arc-inventory routing policy. Int. J. Transp. Sci. Technol. 5, 167–
185. http://dx.doi.org/10.1016/j.ijtst.2016.11.002.
Coifman, B., McCord, M., Mishalani, R.G.R., 2006. Traffic flow data extracted from imagery collected using a micro unmanned aerial vehicle. Appl. Adv.
Technol. Transp. Ninth Int. Conf., pp. 298–303. doi:10.1061/40799(213)47.
Colomina, I., Molina, P., 2014. Unmanned aerial systems for photogrammetry and remote sensing: a review. ISPRS J. Photogramm. Remote Sens. 92, 79–97.
http://dx.doi.org/10.1016/j.isprsjprs.2014.02.013.
Díaz-Vilariño, L., González-Jorge, H., Martínez-Sánchez, J., Bueno, M., Arias, P., 2016. Determining the limits of unmanned aerial photogrammetry for the
evaluation of road runoff. Measurement 85. http://dx.doi.org/10.1016/j.measurement.2016.02.030.
DJI, 2016. Spreading Wings S900 – highly portable, powerful aerial system for the demanding filmmaker [WWW Document]. URL <http://www.dji.com/
product/spreading-wings-s900> (accessed 30.05.16).
Dobson, R.J., Brooks, C., Roussi, C., Colling, T., 2013. Developing an unpaved road assessment system for practical deployment with high-resolution optical
data collection using a helicopter UAV. In: International Conference on Unmanned Aircraft Systems (ICUAS). IEEE, pp. 235–243. doi:10.1109/
ICUAS.2013.6564695.
Doherty, P., Granlund, G., Kuchcinski, K., 2000. The WITAS unmanned aerial vehicle project, ECAI.
Eisenbeiss, H., 2004. A mini unmanned aerial vehicle (UAV): system overview and image acquisition. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci.
Erdelj, M., Natalizio, E., 2016. UAV-assisted disaster management: applications and open issues. 2016 Int. Conf. Comput. Netw. Commun., pp. 1–5.
doi:10.1109/ICCNC.2016.7440563.
European Aviation Safety Agency, 2016. ‘‘Prototype” Commission Regulation on Unmanned Aircraft Operations.
Ezequiel, C.A.F., Cua, M., Libatique, N.C., Tangonan, G.L., Alampay, R., Labuguen, R.T., Favila, C.M., Honrado, J.L.E., Canos, V., Devaney, C., Loreto, A.B., Bacusmo,
J., Palma, B., 2014. UAV aerial imaging applications for post-disaster assessment, environmental management and infrastructure development. 2014 Int.
Conf. Unmanned Aircr. Syst., pp. 274–283. doi:10.1109/ICUAS.2014.6842266.
Federal Aviation Administration, 2016. Summary of Small Unmanned Aircraft Rule. FAA News.
Finn, R.L., Wright, D., 2012. Unmanned aircraft systems: Surveillance, ethics and privacy in civil applications. Comput. Law Secur. Rev. 28, 184–194. http://
dx.doi.org/10.1016/j.clsr.2012.01.005.
Freeman, P.K., Freeland, R.S., 2014. Politics & technology: U.S. polices restricting unmanned aerial systems in agriculture. Food Policy 49, 302–311. http://dx.
doi.org/10.1016/j.foodpol.2014.09.008.
Frew, E., McGee, T., Kim, Z., 2004. Vision-based road-following using a small autonomous aircraft. Aerosp. Conf. 2004. Proceedings. 2004 IEEE 5.
Gao, H., Kong, S.L., Zhou, S., Lv, F., Chen, Q., 2014. Automatic Extraction of Multi-Vehicle Trajectory Based on Traffic Videotaping from Quadcopter Model.
Appl. Mech. Mater. 552, 232–239. http://dx.doi.org/10.4028/www.scientific.net/AMM.552.232.
Gheisari, M., Karan, E., Christmann, H.C., Irizarry, J., Johnson, E.N., 2015. Investigating Unmanned Aerial System (UAS) Application Requirements within a
Department of Transportation. Transportation Research Board 94th Annual Meeting Compendium of Papers.
Granlund, G., Nordberg, K., Wiklund, J., Doherty, P., Skarman, E., Sandewall, E., 2000. WITAS : An Intelligent Autonomous Aircraft Using Active Vision. Proc.
UAV 2000 Int. Tech. Conf. Exhib.
Gupta, S.G., Ghonge, M.M., Jawandhiya, P.M., 2013. Review of unmanned aircraft system. Int. J. Adv. Res. Comput. Eng. Technol. 2, 2278–2323.
Haidari, L.A., Brown, S.T., Ferguson, M., Bancroft, E., Spiker, M., Wilcox, A., Ambikapathi, R., Sampath, V., Connor, D.L., Lee, B.Y., 2016. The economic and
operational value of using drones to transport vaccines. Vaccine 34, 4062–4067. http://dx.doi.org/10.1016/j.vaccine.2016.06.022.
Heintz, F., Rudol, P., Doherty, P., 2007. From images to traffic behavior – A UAV tracking and monitoring application. In: FUSION 2007–2007 10th
International Conference on Information Fusion, IEEE, pp. 1–8. doi:10.1109/ICIF.2007.4408103.
Hsieh, J.-W., Yu, S.-H., Chen, Y.-S., Hu, W.-F., 2006. Automatic traffic surveillance system for vehicle tracking and classification. IEEE Trans. Intell. Transp.
Syst. 7, 175–187. http://dx.doi.org/10.1109/TITS.2006.874722.
Idries, A., Mohamed, N., Jawhar, I., Mohamed, F., Al-Jaroodi, J., 2015. Challenges of developing UAV applications: a project management view, IEOM 2015 –
5th Int. Conf. Ind. Eng. Oper. Manag. Proc. doi:10.1109/IEOM.2015.7093730.
IEEE Spectrum, 2016. Dutch Police Training Eagles to Take Down Drones – IEEE Spectrum [WWW Document]. URL <http://spectrum.ieee.org/automaton/
robotics/drones/dutch-police-training-eagles-to-take-down-drones>.
Jiang, X., Cao, X., 2016. Surveillance from above: a detection-and-prediction based multiple target tracking method on aerial videos. In: 2016 Integrated
Communications Navigation and Surveillance (ICNS). IEEE, Herndon, VA, pp. 1–13. doi:10.1109/ICNSURV.2016.7486348.
Kaaniche, K., Champion, B., Pégard, C., Vasseur, P., 2005. A vision algorithm for dynamic detection of moving vehicles with a UAV. Proc. – IEEE Int. Conf.
Robot. Autom., 78–83 http://dx.doi.org/10.1109/ROBOT.2005.1570387.
Kanistras, K., Martins, G., Rutherford, M.J., Valavanis, K.P., 2014. Survey of Unmanned Aerial Vehicles (UAVs) for traffic monitoring. In: Handbook of
Unmanned Aerial Vehicles. Springer, pp. 2643–2666. doi:10.1109/ICUAS.2013.6564694.
Knoppers, P., van Lint, H., Hoogendoorn, S., 2012. Automatic stabilization of aerial traffic images. Transportation Research Board 91st Annual Meeting.
Knyaz, V.A., Chibunichev, A.G., 2016. Photogrammetric techniques for road surface analysis. In: ISPRS-International Archives of the Photogrammetry,
Remote Sensing and Spatial Information Sciences. Prague, Czech Republic, pp. 515–520. doi:10.5194/isprsarchives-XLI-B5-515-2016.
Lee, J., Zhong, Z., Kim, K., Dimitrijevic, B., Du, B., Gutesa, S., 2015. Examining the applicability of small quadcopter drone for traffic surveillance and roadway
incident monitoring. Transp. Res. Board 94th Annu. Meet. Compend. Pap.
Lenhart, D., Hinz, S., Leitloff, J., Stilla, U., 2008. Automatic traffic monitoring based on aerial image sequences. Pattern Recognit. Image Anal. 18, 400–405.
http://dx.doi.org/10.1134/S1054661808030061.
Li, Y., 2008. Fuzzy Image Segmentation From High Resolution Uav Aerial, ISPRS08. p. B3b 529.
Lima, C., Cardoso, J.L., Ben-Akiva, M.E., Costeira, J.P., Marques, M., Azevedo, C.L., Cardoso, J.L., Ben-Akiva, M.E., Costeira, J.P., Marques, M., 2014. Automatic
Vehicle Trajectory Extraction by Aerial Remote Sensing. Proc. – Soc. Behav. Sci. 111, 849–858. http://dx.doi.org/10.1016/j.sbspro.2014.01.119.
Lin, P.-S., Puri, A., Hagen, L., Valavanis, K., 2006. Automatic transformation of video image data from UAVs into traffic information for simulation model
calibration. ITS World Congr. 13th World Congr. Intell. Transp. Syst. Compend. Tech. Pap. 1–8.
Linchant, J., Lisein, J., Semeki, J., Lejeune, P., Vermeulen, C., 2015. Are unmanned aircraft systems (UASs) the future of wildlife monitoring? A review of
accomplishments and challenges. Mamm. Rev. 45, 239–252. http://dx.doi.org/10.1111/mam.12046.
Liu, Meng, Wu, Chengdong, Zhang, Yunzhou, 2008. A review of traffic visual tracking technology. In: International Conference on Audio, Language and Image
Processing. IEEE, pp. 1016–1020. doi:10.1109/ICALIP.2008.4590198.
Liu, X., Li, L., Peng, Z., Xu, X., 2013. Multi-objective optimization model and evolutionary algorithm to plan UAV cruise route for road traffic surveillance.
Transp. Res. Board 92nd Annu. Meet.
Liu, X., Peng, Z., Hou, H., Wang, L., 2015. Simulation and evaluation of using unmanned aerial vehicle to detect low-volume road traffic incident. Transp. Res.
Board 94th Annu. Meet. Compend. Pap.
Ma, L., Li, M.C., Wang, Y.F., Tong, L.H., Cheng, L., 2013. Using high-resolution imagery acquired with an autonomous unmanned aerial vehicle for urban
construction and planning. Proc. 2013 Int. Conf. Remote Sensing, Environ. Transp. Eng. (Rsete 2013) 31, 200–203.
Mahadevan, P., 2010. The military utility of drones. CSS Anal. Secur. Policy, 1–3.
Maza, I., Caballero, F., Capitán, J., Martínez-De-Dios, J.R., Ollero, A., 2011. Experimental results in multi-UAV coordination for disaster management and civil
security applications. J. Intell. Robot. Syst. Theory Appl. 61, 563–585. http://dx.doi.org/10.1007/s10846-010-9497-5.
Mccarley, J.J.S., Wickens, C.D.C., 2004. Human factors concerns in UAV flight. Urbana-Champaign, Inst. Aviat. 3.1-3.11.
McCormack, E., Trepanier, T., 2008. The use of small unmanned aircraft by the Washington State Department of Transportation.
122 E.N. Barmpounakis et al. / International Journal of Transportation Science and Technology 5 (2016) 111–122

McCoy, J. V., 2003. Unmanned aerial logistics vehicles: a concept worth pursuing? doi:10.1017/CBO9781107415324.004.
Merino, L., Caballero, F., Dios, J.R.M., Ollero, A., 2005. Cooperative fire detection using unmanned aerial vehicles. IEEE Int. Conf. Robot. Autom. 1896–1901.
http://dx.doi.org/10.1109/ROBOT.2005.1570388.
Metni, N., Hamel, T., 2007. A UAV for bridge inspection: Visual servoing control law with orientation limits. Autom. Constr. 17, 3–10. http://dx.doi.org/
10.1016/j.autcon.2006.12.010.
Milgram, J., Strickland, J., Macander, A., Hunter, G., 2003. autonomous glider systems for logistics delivery. AUVSI (Associated Unmanned Veh. Syst. Int. 2003
Unmanned Syst. Symp. Expo. 5301.
Mirchandani, P., Hickman, M., Angel, A., Chandnani, D., Hickman, M., 2002. Application of aerial video for traffic flow monitoring and management. ASCE 7th
Int. Conf. Appl. Adv. Technol. Transp.
Mohammed, F., Idries, A., Mohamed, N., Al-Jaroodi, J., Jawhar, I., 2014. UAVs for smart cities: opportunities and challenges. 2014 Int. Conf. Unmanned Aircr.
Syst. ICUAS 2014 – Conf. Proc., pp. 267–273. doi:10.1109/ICUAS.2014.6842265.
Murray, C.C., Chu, A.G., 2015. The flying sidekick traveling salesman problem: optimization of drone-assisted parcel delivery. Transp. Res. Part C 54, 86–109.
http://dx.doi.org/10.1016/j.trc.2015.03.005.
Namuduri, K., Wan, Y., Gomathisankaran, M., 2013. Mobile ad hoc networks in the sky. Proc. Second ACM MobiHoc Work. Airborne networks Commun. -
ANC ’13 25. doi:10.1145/2491260.2491265.
Ordoukhanian, E., Madni, A.M., 2016. Resilient Multi-UAV Operations: key concepts and challenges, 54th AIAA Aerospace Sciences Meeting. p. 475.
Papageorgiou, M., Diakaki, C., Dinopoulou, V., Kotsialos, A., Wang, Y., 2008. Review of road traffic control strategies. Proc. IEEE 91, 2043–2067.
PB Farradyne, 2005. Use of Unmanned Aerial Vehicles in Traffic Surveillance and Traffic Management. This is an online report that can be found in: <http://
www.i95coalition.org/wp-content/uploads/2015/03/Report_TechMemo_UAV_FL.pdf>.
Puri, A., Valavanis, K., Kontitsis, M., 2007. Statistical profile generation for traffic monitoring using real-time UAV based video data. Mediterr. Conf. Control
Autom. 1–6. http://dx.doi.org/10.1109/MED.2007.4433658.
Raffaelle, D., 2014. Can drones deliver? IEEE Trans. Autom. Sci. Eng. 11, 647–648. http://dx.doi.org/10.1109/TASE.2014.2326952.
Reinartz, P., Lachaise, M., Schmeer, E., Krauss, T., Runge, H., 2006. Traffic monitoring with serial images from airborne cameras. ISPRS J. Photogramm. Remote
Sens. 61, 149–158. http://dx.doi.org/10.1016/j.isprsjprs.2006.09.009.
Ro, K., Oh, J., Dong, L., 2007. Lessons learned: Application of small uav for urban highway traffic monitoring, 45th AIAA Aerosp. Sci. Meet. Exhib., pp. 1–19.
doi:10.2514/6.2007-596.
Rodriguez-Canosa, G.R., Thomas, S., del Cerro, J., Barrientos, A., MacDonald, B., 2012. A real-time method to detect and track moving objects (DATMO) from
Unmanned Aerial Vehicles (UAVs) using a single camera. Remote Sens. 4, 1090–1111. http://dx.doi.org/10.3390/rs4041090.
Salvo, G., Caruso, L., Scordo, A., 2013. Gap acceptance analysis in an urban intersection through a video acquired by an UAV 199–205.
Salvo, G., Caruso, L., Scordo, A., 2014a. Urban traffic analysis through an UAV. Proc. – Soc. Behav. Sci. 111, 1083–1091. http://dx.doi.org/10.1016/j.
sbspro.2014.01.143.
Salvo, G., Caruso, L., Scordo, A., Guido, G., 2014. Comparison between vehicle speed profiles acquired by differential GPS and UAV, 17th Meet. EURO Work.
Gr. Transp. EWGT.
Sapkota, K.R., Roelofsen, S., Rozantsev, A., Lepetit, V., Gillet, D., Fua, P., Martinoli, A., 2016. Vision-based unmanned aerial vehicle detection and tracking for
sense and avoid systems 1556–1561.
Sbeiti, M., Goddemeier, N., Behnke, D., Wietfeld, C., 2016. PASER: secure and efficient routing approach for airborne mesh networks. IEEE Trans. Wirel.
Commun. 15, 1950–1964. http://dx.doi.org/10.1109/TWC.2015.2497257.
Shastry, A., Schowengerdt, R., 2002. Airborne video registration for visualization and parameter estimation of traffic flows. Proc. Pecora. 15, 391–405.
Shukla, A.P., Saini, M., 2015. Moving object tracking of vehicle detection: a concise review. Int. J. Signal Process. Image Process. Pattern Recognit. 8, 169–176.
Siebert, S., Teizer, J., 2014. Mobile 3D mapping for surveying earthwork projects using an Unmanned Aerial Vehicle (UAV) system. Autom. Constr. 41, 1–14.
http://dx.doi.org/10.1016/j.autcon.2014.01.004.
Sivaraman, S., Trivedi, M.M., 2013. Integrated lane and vehicle detection, localization, and tracking: a synergistic approach. IEEE Trans. Intell. Transp. Syst.
14, 906–917. http://dx.doi.org/10.1109/TITS.2013.2246835.
Srinivasan, S., Latchman, H., Shea, J., 2004. Airborne traffic surveillance systems: video surveillance of highway traffic. Proc. ACM 2nd Int. Work. Video
Surveill. Sens. networks, pp. 131–135.
Su, B., Wang, H., Liang, X., Ji, H., 2014. Moving objects detecting and tracking for unmanned aerial vehicle. In: Sun, F., Hu, D., Liu, H. (Eds.), Foundations and
Practical Applications of Cognitive Systems and Information Processing, Springer, Berlin Heidelberg, pp. 317–333. doi:10.1007/978-3-642-37835-5.
Vlahogianni, E.I., 2015. Computational Intelligence and Optimization for Transportation Big Data: Challenges and Opportunities, Volume 1-. ed, Engineering
and Applied Sciences Optimization. Springer International Publishing. doi:10.1007/978-3-319-18320-6_7.
Vlahogianni, E.I., Barmpounakis, E.N., 2017. Gamification and sustainable mobility: challenges and opportunities in a changing transportation landscape. In:
Hussein, D. (Ed.), Low Carbon Mobility for Future Cities. Institution of Engineering and Technology.
Wang, H., Duan, S., Zheng, Y., Liu, S., Dong, C., Li, Y., 2014. Using model aircraft to collect vehicle trajectory data. Transp. Res. Board 93rd Annu. Meet.
Compend. Pap.
Wang, L., Chen, F., Yin, H., 2015. Detecting and tracking vehicles in traffic by unmanned aerial vehicles. Autom. Constr. doi:10.1016/j.autcon.2016.05.008.
Watts, A.C., Ambrosia, V.G., Hinkley, E.A., 2012. Unmanned aircraft systems in remote sensing and scientific research: classification and considerations of
use. Remote Sens. 4, 1671–1692. http://dx.doi.org/10.3390/rs4061671.
Wu, D., Arkhipov, D.I., Kim, M., Talcott, C.L., Regan, A.C., McCann, J.A., Venkatasubramanian, N., 2016. ADDSEN: adaptive data processing and dissemination
for drone swarms in urban sensing. IEEE Trans. Comput. 1–1. http://dx.doi.org/10.1109/TC.2016.2584061.
Xin, Z., Yun-tao, C., Li, L., Jia-ning, G., 2014. Algorithm of Vehicle Speed Detection in Unmanned Aerial Vehicle Videos. In: Transportation Research Board
93rd Annual Meeting Compendium of Papers. Washington, D.C.
Yu Min Chen, L.D., Oh, J., 2007. Real-Time Video Relay for UAV traffic surveillance systems through available communication networks. In: Wireless
Communications and Networking Conference, IEEE, pp. 2608–2612. doi:10.1109/WCNC.2007.485.
Zhang, C., 2006. A UAV-Based photogrammetric mapping system. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. XXXVII, 627–631.
Zhang, C., Elaksher, A., 2012. An unmanned aerial vehicle-based imaging system for 3D measurement of unpaved road surface distresses. Comput. Civ.
Infrastruct. Eng. 27, 118–129. http://dx.doi.org/10.1111/j.1467-8667.2011.00727.x.
Zhang, L., Peng, Z., Sun, D.D.J., Liu, X., 2013. A UAV-based automatic traffic incident detection system for low volume roads. Transp. Res. Board 92nd Annu.
Meet., pp. 1–19.
Zhang, L., Peng, Z., Li, L., 2014. A novel road boundary detection approach for not-well-marked roads in UAV video. Transportation Research Board 93rd
Annual Meeting Compendium of Papers.
Zhao, Y., Pei, H., 2012. An improved vision-based algorithm for unmanned aerial vehicles autonomous landing. Phys. Procedia 33, 935–941. http://dx.doi.
org/10.1016/j.phpro.2012.05.157.
Zhou, H., Kong, H., Wei, L., Creighton, D., Nahavandi, S., 2015a. Efficient road detection and tracking for unmanned aerial vehicle. IEEE Trans. Intell. Transp.
Syst. 16, 297–309. http://dx.doi.org/10.1109/TITS.2014.2331353.
Zhou, Y., Cheng, N., Lu, N., Shen, X.(Sherman), 2015b. Multi-UAV-aided networks: aerial-ground cooperative vehicular networking architecture. IEEE Veh.
Technol. Mag. 10, 36–44.