*Article* **Utilizing UAVs Technology on Microscopic Traffic Naturalistic Data Acquirement**

**Apostolos Anagnostopoulos and Fotini Kehagia \***

Highway Laboratory, Division of Transportation and Construction Management, School of Civil Engineering, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece; aposanag@civil.auth.gr

**\*** Correspondence: fkehagia@civil.auth.gr; Tel.: +30-2310-994380

**Abstract:** Research into collecting and measuring reliable, accurate, and naturalistic microscopic traffic data is a fundamental aspect in road network planning scientific literature. The vehicle trajectory is one of the main variables in traffic flow theory that allows to extract information regarding microscopic traffic flow characteristics. Several methods and techniques have been applied regarding the acquisition of vehicle trajectory. The forthcoming applications of intelligent transport systems on vehicles and infrastructure require sufficient and innovative tools to calibrate existing models on more complex situations. Unmanned aerial vehicles (UAVs) are one of the most emerging technologies being used recently in the transportation field to monitor and analyze the traffic flow. The aim of this paper is to examine the use of UAVs as a tool for microscopic traffic data collection and analysis. A comprehensive guiding framework for accurate and cost-effective naturalistic traffic surveys and analysis using UAVs is proposed and presented in detail. Field experiments of acquiring vehicle trajectories on two multilane roundabouts were carried out following the proposed framework. Results of the experiment indicate the usefulness of the UAVs technology on various traffic analysis studies. The results of this study provide a practical guide regarding vehicle trajectory acquirement using UAVs.

**Keywords:** UAVs; naturalistic vehicle trajectories; microscopic traffic data; traffic data collection; guiding framework

## **1. Introduction**

*1.1. Microscopic Traffic Data Acquirement*

Research into collecting and measuring reliable microscopic traffic data is a fundamental aspect in road network planning scientific literature. Several applications can be implemented by using the acquired dataset in terms of traffic safety, road capacity, and level of service analysis [1–4]. However, as the traffic conditions get more complex, the level of detail and the quality of the collected information is getting higher.

The forthcoming applications of intelligent transport systems on vehicles and infrastructure mean that existing road layouts need to be examined across a wider range of scenarios [5]. As new technologies are applied to transport systems, accurate calibration and validation approaches of microscopic traffic flow models are essential. Driver behavior modelling, especially in complex scenarios and dynamic environments, such as roundabouts, is challenging and depends mainly on the size and the variety of the obtained data [6]. A dataset of accurate and high detailed microscopic traffic data can improve the reliability of models and allow a sufficient traffic analysis.

The vehicle trajectory is one of the main variables in traffic flow theory that allows to extract information regarding microscopic traffic flow characteristics [7–9]. The ability to extract the position of the vehicles over time along the roadway can provide an understanding of the way vehicles move and a comprehensive dataset for implementation in several applications regarding traffic flow and safety analysis [10,11].

**Citation:** Anagnostopoulos, A.; Kehagia, F. Utilizing UAVs Technology on Microscopic Traffic Naturalistic Data Acquirement. *Infrastructures* **2021**, *6*, 89. https:// doi.org/10.3390/infrastructures6060089

Academic Editors: Krzysztof Goniewicz, Robert Czerski and Marek Kustra

Received: 16 May 2021 Accepted: 10 June 2021 Published: 16 June 2021

**Publisher's Note:** MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.

**Copyright:** © 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/).

Several data collection techniques are used regarding the acquisition of vehicle trajectory [12–17]. Each one is characterized by its potential capabilities and limitations. Thus, the selection of the proper technique for the execution of the survey is strongly related to the level of detail, accuracy and the purpose of the study. The most common methods, as have been identified according to the literature, are summarized in the following: (a) application of global positioning systems (GPS), (b) video processing techniques, (c) applications based on smartphone device technology, and (d) on satellite navigation systems.

However, a main challenge for researchers and traffic engineers is the ability to extract accurate and naturalistic traffic data. Data mining techniques by acquiring accurate traffic data from naturalistic driving behavior is a remarkable and active field of research during last years. Several applications can be found in the scientific literature addressing these issues [18,19]. Nevertheless, it is noted that in most vehicle trajectory studies, collected data lack naturalness, as experiments are conducted under the awareness of the drivers. Thus, the necessary quality of the dataset is weak in terms of representing the actual driving behavior.

In the last years, video image processing techniques are applied more frequently as they represent a low-cost and non-infrastructure-based method for acquiring naturalistic vehicle trajectories [5,20]. Several studies have been developed by extracting traffic data from recorded videos.

In this context, unmanned aerial vehicles (UAVs) are one of the most emerging technologies being used recently in the transportation field to monitor and analyze the traffic flow. UAV image acquisition technologies have been developed and allow to extract and analyze the traffic information in a sufficient way.

#### *1.2. UAV Technology for Traffic Surveys and Analysis*

UAVs can be integrated in various applications of the transport engineering sector, such as road safety inspections, traffic analysis and damage assessment for roads [21–25]. The benefits of deploying UAVs for traffic monitoring and analysis have been considered in several studies in the past few years [5,20,26–28]. As the camera is in the air, the drivers' attitude is not distracted by the equipment. According to this, extracted data represent naturalistic driving behavior which is significant for the study of vehicle trajectories. Moreover, UAVs require less experience and training to be controlled while they can handle a wide field of view, covering large areas quickly. These assets result in a timesaving, low-cost, and non-infrastructure-based technique for acquiring individual vehicle trajectories, compared to other methods.

However, as UAVs are rapidly growing in popularity and their technology is improving constantly, the implemented applications on transportation sector have not fully developed yet. Considering this, several limitations can be identified [11,29,30]. There are many factors that influence the performance of this process. Among them, weather conditions (e.g., rain), technical issues (e.g., low battery duration), and regulatory issues (e.g., no-fly zones) are the most critical to be mentioned. Thus, the ability to select and implement UAVs as an efficient traffic survey tool depends on many aspects. Table 1 summarizes the main benefits and limitations of using UAVs for traffic surveys.

**Table 1.** The main benefits and limitations of using UAVs for traffic surveys.


The aim of this paper is to examine the use of UAVs as a tool for microscopic traffic data collection and analysis. A comprehensive guiding framework for accurate and costeffective naturalistic traffic surveys using UAVs is proposed and presented in detail. An experiment involving the acquisition of vehicle trajectories on two multilane roundabouts is described. Finally, the utility of UAVs regarding microscopic traffic data acquirement is discussed based on the literature review and the analyzed guiding framework of the study.
