Vehicle trajectories collected by a swarm of drones in Athens, Greece

This dataset contains highly detailed, georeferenced vehicle trajectories collected by a swarm of eight drones operating over the city centre of Athens, Greece. In total, it includes more than 800,000 unique trajectories captured across 10 distinct urban locations. Each trajectory is recorded with high temporal resolution, with vehicle positions sampled at a frequency of 25 data points per second.

Data collection

The drone flights were conducted during both the morning and afternoon peak traffic periods over five consecutive days, from May 20th to 24th, 2024. Morning recording sessions took place between 7:00 AM and 10:00 AM, while afternoon sessions were carried out from 3:00 PM to 5:00 PM. 

Each drone was positioned to hover steadily over a predefined location, capturing high-resolution video at 4K quality and a frame rate of 25 frames per second. In most cases, each drone was assigned to monitor a single scene; however, drones D3 and D8 were each deployed across two different locations. A detailed list of all recorded locations is provided below.

Scene ID
Drone ID
Location
Coordinates
Recording

1A
D1
Platia Omonias
(37.9839032, 23.7283130)

2024-05-20

2024-05-21

2024-05-22

2024-05-23

2024-05-24

2A

D2
Sokratous
(37.9806595, 23.7258654)

2024-05-20

2024-05-21

2024-05-22

2024-05-23

2024-05-24

3A
D3
Stadiou - Dragatsaniou
(37.9799178, 23.7313515)

2024-05-20 AM

2024-05-21 AM

2024-05-22 AM

2024-05-23 AM

2024-05-24 AM

3B
D3
Stadious - loannou Paparrigopoulou
(37.9789367, 23.7313973)

2024-05-20 PM

2024-05-21 PM

2024-05-22 PM

2024-05-23 PM

2024-05-24 PM

4A
D4
Panepistimiou
(37.9801466, 23.7334397)

2024-05-20

2024-05-21

2024-05-22

2024-05-23

5A
D5
Akadimias
(37.9819656, 23.7339652)

2024-05-21

2024-05-22

2024-05-23

2024-05-24

6A
D6
Vassilis Amalias - Vassilis Sofias
(37.9761971, 23.7357609)

2024-05-20

2024-05-21

2024-05-22

2024-05-23

2024-05-24

7A
D7
Plateia Syntagmatos
(37.9755723, 23.7341740)

2024-05-20

2024-05-21

2024-05-22

2024-05-23

2024-05-24

8A
D8
Vassilis Amalias
(37.9696032, 23.7314880)

2024-05-20 - 

2024-05-21

2024-05-22

2024-05-23

2024-05-24

8B
D8
Vasileos Konstantinou
(37.9698524, 23.7397584)

2024-05-20

2024-05-21

2024-05-22

2024-05-23

2024-05-24

File and data structure 

The dataset is organized into a collection of compressed ZIP archives, with each file corresponding to a specific combination of recording date and scene. The naming convention for these archives follows the format:

Date_SceneID

Date: recording date in the format YYYY-MM-DD

SceneID: identifier of the drone (1A, 2A, ... 8B)

Each ZIP archive contains multiple CSV files, where each file represents the vehicle trajectories extracted from a single recorded video. The CSV filenames follow a structured naming convention:

Date_DroneID_SessionID_SceneID-VideoNumber

Date: recording date (YYYY-MM-DD)

DroneID: drone identifier (D1, D2, ..., D8)

SessionID: identifier of the flight session (e.g., AM1, AM2, …, PM1, PM2). “AM” denotes morning sessions, while “PM” refers to afternoon sessions

SceneID: scene identifier (from the list of locations above)

VideoNumber: index of the video within the corresponding flight session

For example, the file 2024-05-20_D1_AM1_1A-1.csv contains trajectory data from the first video of scene 1A, recorded on May 20, 2024, by drone D1 during the first morning session.

Data structure

Each csv file is structured into 7 columns and each row represents one datapoint.  

Column Name
Data Type
Description

veh_id
Integer
Unique vehicle ID per video (1, 2,...)

veh_type
String
Vehicle category (Car, Truck, Bus, Motorcycle)

lon
Float
Longitude in decimal degrees (EPSG:4326)

lat
Float
Latitude in decimal degrees (EPSG:4326)

datetime
String
Local time in the format YYYY-MM-DD hh:mm:ss.sss

time(s)
Float
Time since the start of the video (s)

speed(km/h)
Float
Estimation of the instantaneous speed (km/h).