This database gives an overview of the specifications of 93 unmanned aerial vehicles (UAVs). This database can be used to characterize different types of UAVs and their properties. The database contains the following information for each UAV: - Maximum takeoff weight (MTOW) - Payload - Wingspan - Lenght - Cruise speed - Maximum speed - Stall speed - Range - Endurance - Altitude - Airfoil - Aspect ratio - Chord length (estimated) - Propeller diameter - UAV type

Dataset description

Based on databases, scientific and internet publications, this dataset lists small armed UAVs and missiles deployed and used worldwide, as well as systems under research and development, with their properties. Non-armed UAVs are included to investigate the global usage of small UAVs and thus overall interest in smaller systems. This comprises non-armed systems which could be provided with or used as weapons.

The two datasets list properties of small and very small UAVs below 2 m size (wingspan, length and rotor diameter) and of missiles with diameters below 69 mm. Currently (Version 2.0) the datasets are comprised of 152 UAVs and 50 missiles, respectively.

In order to minimise a contribution to proliferation of these systems, only public sources were investigated, i.e. the internet as well as publicly available databases and catalogues. Furthermore, where information is incomplete, no estimates based on the laws of physics or stemming from engineering expertise are given. Improvised or modified versions of UAVs or missiles, already in use by non-state actors, are left out for the same reason.

As far as has been available, for UAVs the basic properties with the year of introduction are listed to allow statements on trends of UAV capabilities in recent years. Due to the sheer number of UAV types available today, we focused mainly on UAVs intended to fulfil military roles, such as reconnaissance or combat. An exception are UAVs that fall under the very small (<0.2 m) category. There, most UAVs are still in the research or development stages and not in military service nor designed for military use. However, research and development (R&D) of some systems had been funded originally by military institutions. In any case, these projects are important indicators of the future potential of these small-sized aircraft.

Project Webpage

The datasets are a part of the research project "Preventive Arms Control for Small and Very Small Aircraft and Missiles" of TU Dortmund University. The project has been funded by the German Foundation for Peace Research (DSF, https://bundesstiftung-friedensforschung.de/) in its funding line "New Technologies: Risks and Chances for International Security and Peace".

For a full description of this project, visit https://url.tu-dortmund.de/pacsam.

Unmanned Aerial Vehicles Dataset:

The Unmanned Aerial Vehicle (UAV) Image Dataset consists of a collection of images containing UAVs, along with object annotations for the UAVs found in each image. The annotations have been converted into the COCO, YOLO, and VOC formats for ease of use with various object detection frameworks. The images in the dataset were captured from a variety of angles and under different lighting conditions, making it a useful resource for training and evaluating object detection algorithms for UAVs. The dataset is intended for use in research and development of UAV-related applications, such as autonomous flight, collision avoidance and rogue drone tracking and following. The dataset consists of the following images and detection objects (Drone):

    Subset
    Images
    Drone


    Training
    768
    818


    Validation
    384
    402


    Testing
    383
    400

It is advised to further enhance the dataset so that random augmentations are probabilistically applied to each image prior to adding it to the batch for training. Specifically, there are a number of possible transformations such as geometric (rotations, translations, horizontal axis mirroring, cropping, and zooming), as well as image manipulations (illumination changes, color shifting, blurring, sharpening, and shadowing).

NOTE If you use this dataset in your research/publication please cite us using the following

Rafael Makrigiorgis, Nicolas Souli, & Panayiotis Kolios. (2022). Unmanned Aerial Vehicles Dataset (1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7477569

The data are UAV (Unmanned Aerial Vehicle) and individual tree ground measurements collected from 2 citrus rootstock trials at the U.S. Horticultural Research Laboratory Picos Road farm site, Ft. Pierce, Florida, USA located at 27.437115254946757, -80.42786069428246. The trees in both trials were Valencia sweet orange scion grafted onto various rootstock selections and varieties. The trials are designated as Valencia 5-16 and Valencia 17-28, which indicate the row numbers used for each trial. Valencia 5-16 includes 648 trees and Valencia 17-28 includes 643 trees. The ground data was taken for the 5-16 and 17-28 trials in 2020 and 2021, respectively. The UAV images were taken twice the same day, 5/12/2021, once each under partially sunny (images 27-176) and overcast conditions (images 177-327). A single flight of rows 5-28 for each condition captured both trials. Some of the images under the partially sunny condition show tree shadows when the sun was not obscured behind a cloud, whereas the images under the overcast condition flight have uniform lighting and no sun shadows. Each image is notated to designate the flight condition. For example, the image labeled DJI_0033_R5-R28_Valencia_sunny.JPG was taken from the partially sunny flight and the image labeled DJI_0183_R5-R28_Valencia_overcast.JPG was taken from the overcast flight. The UAV images were taken using a DJI Phantom 4 Pro drone using a side-overlap of 80% and a forward-overlap of 80% of the flight lines. The images are suitable for orthorectification. The images were red-green-blue (sRGB) in a 3:2 format with 5472 x 3648 pixels. The dataset is included in one folder that contains 305 files – 301 image files, 2 Excel spreadsheets (one for each trial) that contain the planting plan and ground measures, and 2 images with the rows and tree spaces labeled. The 2 labeled images are composite images constructed from the 150 images from the overcast set and were created to label rows and tree space numbers. The composite image is useful for general orientation and matching the individual trees to the ground data and other post-processing image analyses.

This dataset provides audio recordings of small unmanned aerial systems (SUAS)

Uav Palm Data

## Overview

Uav Palm Data is a dataset for object detection tasks - it contains Palms annotations for 1,803 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Snapshot img

Electric Unmanned Aerial Vehicle Market Size 2024-2028

The electric unmanned aerial vehicle (E-UAV) market size is forecast to increase by USD 6.54 billion at a CAGR of 16.6% between 2023 and 2028.

The market is witnessing significant growth, driven by the development of powerful electric engines. This advancement enables E-UAVs to fly longer and carry heavier payloads, expanding their applications in various industries. Another key trend is the rapid adoption of sensor fusion technology, which enhances the accuracy and reliability of data collected by E-UAVs. The shift towards greenhouse gas emission reduction has accelerated the adoption of fuel cells and power generation technology, enhancing energy density and specific energy through the use of lithium-ion batteries. However, challenges such as SWaP (Size, Weight, and Power) constraints and network-based limitations persist. Manufacturers are addressing these challenges by innovating lightweight and efficient designs and improving communication technologies. Overall, the E-UAV market is poised for continued expansion, offering substantial opportunities for stakeholders.

What will be the Size of the Electric Unmanned Aerial Vehicle (E-UAV) Market During the Forecast Period?

Request Free Sample

The market is experiencing significant growth due to the emergence of this technology as a cost-effective and environmentally-friendly alternative to traditional manned aircraft. Remote data collection and analysis are key drivers, with e-UAVs offering improved performance through advanced propulsion systems and electrical systems.
Moreover, autonomous e-UAVs employ vision-based and non-vision-based techniques for navigation, with applications spanning various industries, including civil and military sectors. Lighter-than-air, fixed-wing, rotary-wing, bio-mimicry e-UAVs, and multi-e-UAV systems are transforming sectors like surveillance, disaster management, and communication networks. Ground control stations and sensors enable real-time payload data transmission, expanding the potential for civil and military applications.

How is this Electric Unmanned Aerial Vehicle (E-UAV) Industry segmented and which is the largest segment?

The electric unmanned aerial vehicle (E-UAV) industry research report provides comprehensive data (region-wise segment analysis), with forecasts and estimates in 'USD billion' for the period 2024-2028, as well as historical data from 2018-2022 for the following segments.

Application

  Battery
  Solar
  Fuel cell


Geography

  North America

    US


  APAC

    China


  Europe

    France


  South America



  Middle East and Africa

By Application Insights

The battery segment is estimated to witness significant growth during the forecast period.

Electric Unmanned Aerial Vehicles (E-UAVs) are powered by electric motors, which derive power from stored energy in batteries. The selection of batteries is crucial, with parameters such as efficiency, life span, discharge rate, and charge density being key considerations. Li-ion batteries have gained popularity due to the increasing demand for UAVs. However, their efficiency is affected by the repetition of chemical processes during charging and discharging. Furthermore, the charge retention capacity of a Li-ion battery decreases by 30% within a year or after 1,000 cycles. Long-range E-UAVs require larger batteries, which add to the weight and complexity of the vehicle. Hybrid powertrains, which combine electric and fuel-based power, offer a solution to the energy limitations of batteries. Silent operation is a significant advantage of E-UAVs, with minimal noise and gaseous emissions. The market for E-UAVs is growing, with key players focusing on improving battery technology and hybrid powertrains to enhance performance and efficiency.

Get a glance at the Electric Unmanned Aerial Vehicle (E-UAV) Industry report of share of various segments Request Free Sample

The battery segment was valued at USD 3.63 billion in 2018 and showed a gradual increase during the forecast period.

Regional Analysis

North America is estimated to contribute 40% to the growth of the global market during the forecast period.

Technavio's analysts have elaborately explained the regional trends and drivers that shape the market during the forecast period.

For more insights on the market share of various regions, Request Free Sample

The United States market for Electric Unmanned Aerial Vehicles (E-UAVs) is experiencing growth due to the country's expansive geographic borders, making it necessary for continuous coverage in hard-to-reach areas. The US border patrol forces require E-UAVs with extended endurance and lower operational costs to meet their operational needs. Additionally, the significant use of tactical UAVs in military and defense applications has led to an increased procurement of small UAV

This experiment was performed in order to empirically measure the energy use of small, electric Unmanned Aerial Vehicles (UAVs). We autonomously direct a DJI ® Matrice 100 (M100) drone to take off, carry a range of payload weights on a triangular flight pattern, and land. Between flights, we varied specified parameters through a set of discrete options, payload of 0 , 250 g and 500 g; altitude during cruise of 25 m, 50 m, 75 m and 100 m; and speed during cruise of 4 m/s, 6 m/s, 8 m/s, 10 m/s and 12 m/s. We simultaneously collect data from a broad array of on-board sensors. The onboard sensors used to collect these data are* Wind sensor: FT Technologies FT205 UAV-mountable, pre-calibrated ultrasonic wind sensor with accuracy of ± 0.1 m/s and refresh rate of 10 Hz.;* Position: 3DM-GX5-45 GNSS/INS sensor pack. These sensors use a built-in Kalman filtering system to fuse the GPS and IMU data. The sensor has a maximum output rate of 10Hz with accuracy of ± 2 m$ RMS horizontal, ± 5 m$ RMS vertical.* Current and Voltage: Mauch Electronics PL-200 sensor. This sensor can record currents up to 200 A and voltages up to 33 V. Analogue readings from the sensor were converted into a digital format using an 8 channel 17 bit analogue-to-digital converter (ADC).Data syncing and recording was handled using the Robot Operating System (ROS) running on a low-power Raspberry Pi Zero W. Data was recorded on the Raspberry Pi's microSD card. The data provided by each sensor were synchronized to a frequency of approximately 5Hz using the ApproximateTime message filter policy of Robot Operating System (ROS). The number of flights performed varying operational parameters (payload, altitude, speed) was 196. In addition, 13 recordings were done to assess the drone’s ancillary power and hover conditions.

The global UAV Data Transmission Terminal market is poised for significant expansion, projected to reach an estimated market size of $210 million in 2025 with a robust Compound Annual Growth Rate (CAGR) of 5%. This growth trajectory is primarily fueled by the escalating adoption of Unmanned Aerial Vehicles (UAVs) across both military and civilian sectors. In military applications, the demand for secure and high-bandwidth data transmission is critical for advanced surveillance, reconnaissance, and operational command and control. Concurrently, the burgeoning use of civilian drones for applications such as aerial photography, agricultural monitoring, infrastructure inspection, and delivery services is creating substantial market opportunities. The evolution towards more sophisticated drone functionalities, requiring real-time data processing and transmission, further accentuates the need for advanced data transmission terminals. Furthermore, the continuous development of communication technologies, including the integration of 5G networks and improved radio frequencies like 433MHz and 915MHz, is enhancing the capabilities and reliability of these terminals, driving market penetration. The market landscape is characterized by intense competition, with major defense contractors like Lockheed Martin, Raytheon, and BAE Systems playing a significant role alongside specialized UAV communication providers such as DJI and Elsight. China Electronics Technology Group Corporation's research institutes are also emerging as key players, particularly in the Asia Pacific region. While the market is driven by innovation and increasing drone deployment, it faces certain restraints. These include stringent regulatory frameworks governing drone operations and data transmission, particularly concerning security and privacy, which can slow down adoption in some regions. Additionally, the high cost associated with advanced data transmission systems and the need for skilled personnel to operate and maintain them can pose challenges for smaller enterprises. Despite these hurdles, the overarching trend towards miniaturization, increased data throughput, and enhanced security features in UAV data transmission terminals suggests a dynamic and expanding market in the coming years. This report offers a deep dive into the dynamic UAV Data Transmission Terminal market, encompassing a detailed analysis from 2019 to 2033, with a focus on the base and estimated year of 2025 and a forecast period extending to 2033. The study meticulously examines historical trends, current market dynamics, and future projections, providing actionable insights for stakeholders.

A sampling of reports involving Unmanned Aerial Vehicle (UAV) events.

Snapshot img

UAV Market Size 2025-2029

The UAV market size is forecast to increase by USD 37.53 billion, at a CAGR of 15.1% between 2024 and 2029.

The market is experiencing significant growth, driven by increasing defense spending on unmanned technologies. This trend is particularly noticeable in the defense and security sector, where UAVs are increasingly being used for surveillance, reconnaissance, and border patrol. Another key driver is the development of alternate propulsion technologies for UAVs, which are addressing size, weight, and power (SWaP) challenges. However, the market also faces significant hurdles, such as the need for greater bandwidth to support real-time data transmission and the increasing complexity of UAV systems. In the agriculture industry, precision farming is a significant application area for UAVs, enabling farmers to monitor crop health, optimize irrigation, and improve yields.
In the energy sector, UAVs are used for pipeline inspections and monitoring of solar and wind farms. Despite these opportunities, the challenges of bandwidth and SWaP constraints remain significant obstacles to wider adoption in these sectors. Companies seeking to capitalize on the market's potential must focus on developing innovative solutions to address these challenges while meeting the specific requirements of defense, agriculture, and energy applications.

What will be the Size of the UAV Market during the forecast period?

Explore in-depth regional segment analysis with market size data - historical 2019-2023 and forecasts 2025-2029 - in the full report.
Request Free Sample

The market continues to evolve, with dynamic applications across various sectors. Terrain mapping and data processing are crucial components, enhancing infrastructure monitoring, forestry management, and environmental conservation. Precision agriculture utilizes multispectral imaging and data acquisition for optimized crop yields. Mining applications leverage drones for exploration and inspection services. Emergency response teams employ UAVs for search and rescue missions and aerial surveillance. Commercial drone operations offer diverse services, including delivery, inspection, and photography. Military applications incorporate advanced navigation systems, anti-drone technology, and drone detection systems for security and surveillance. Drone racing and recreational use add to the market's vibrant ecosystem.

Video analytics, thermal imaging, and software integration provide valuable insights for industries like law enforcement, border security, and wildlife conservation. The ongoing development of UAV hardware, flight control systems, and pilot training ensures continuous innovation. Safety protocols and counter-UAV measures ensure responsible use and mitigate potential risks. UAVs are transforming industries, from construction monitoring and supply chain management to real estate photography and event coverage. The future of this market is characterized by ongoing advancements, integrating new technologies and applications.

How is this UAV Industry segmented?

The uav industry research report provides comprehensive data (region-wise segment analysis), with forecasts and estimates in 'USD million' for the period 2025-2029, as well as historical data from 2019-2023 for the following segments.

Type

  Rotary wing
  Fixed wing
  Hybrid


Application

  Defense and homeland security
  Commercial and civil
  Consumer


Class Type

  Small UAVs
  Tactical UAVs
  Micro UAVs


Distribution Channel

  OEM Sales
  Online Retail
  Specialty Stores
  Distributors
  Others


Geography

  North America

    US
    Canada


  Europe

    France
    Germany
    Italy
    UK


  Middle East and Africa

    Egypt
    KSA
    Oman
    UAE


  APAC

    China
    India
    Japan


  South America

    Argentina
    Brazil


  Rest of World (ROW)

By Type Insights

The rotary wing segment is estimated to witness significant growth during the forecast period.

The market encompasses various applications, including terrain mapping, data processing, precision agriculture, mining, emergency response, construction monitoring, commercial operations, military applications, drone racing, video analytics, drone delivery, data acquisition, multispectral imaging, drone maintenance, pilot training, navigation systems, software integration, thermal imaging, open-source platforms, border security, wildlife conservation, law enforcement, aerial surveillance, drone photography, supply chain management, and more. The military sector is a significant contributor to the market's growth due to increasing security concerns and government funding. Rotary wing UAVs, which fly using revolving rotor blades, are gaining popularity in military applications for intelligence, reconnaissance, and surveillance. Additionally, UAVs are employed in industries such as agriculture, mining

STAQS_Drone_Data is the PM 2.5 data collected by the BlueHalo E900 UAV during the Synergistic TEMPO Air Quality Science (STAQS) mission. Data collection for this product is complete.Launched in April 2023, NASA’s Tropospheric Emissions: Monitoring of Pollution (TEMPO) satellite monitors major air pollutants across North America every daylight hour at high spatial resolution at a geostationary orbit (GEO). With these measurements, NASA’s STAQS mission seeks to integrate TEMPO satellite observations with traditional air quality monitoring to improve understanding of air quality science. STAQS is being conducted during summer 2023, targeting urban areas, including Los Angeles, New York City, and Chicago. As part of the mission two aircraft will be outfitted with various remote sensing payloads. The Johnson Space Center (JSC) Gulfstream-V (G-V) aircraft will feature the GeoCAPE Airborne Simulator (GCAS) and combined High Spectral Resolution Lidar-2 (HSRL-2) and Ozone Differential Absorption Lidar (DIAL). This payload provides repeated high-resolution mapping of NO2, HCHO, ozone, and aerosols up to 3x per day over targeted cities. NASA Langley Research Center’s (LaRC’s) Gulfstream-III will measure city-scale emissions 2x per day over the targeted cities with the High-Altitude Lidar Observatory (HALO) and Airborne Visible InfraRed Imaging Spectrometer – Next Generation (AVIRS-NG). STAQS will also incorporate ground-based tropospheric ozone profiles from the NASA Tropospheric Ozone Lidar Network (TOLNet), NO2, HCHO, and ozone measurements from Pandora spectrometers, and will leverage existing networks operated by the EPA and state air quality agencies. The primary goal of STAQS is to improve our current understanding of air quality science under the TEMPO field of regard. Further goals include evaluating TEMPO level 2 data products, interpreting the temporal and spatial evolution of air quality events tracked by TEMPO, improving temporal estimates of anthropogenic, biogenic, and greenhouse gas emissions, and assessing the benefit of assimilating TEMPO data into chemical transport models.

The Unmanned Aircraft System (UAS) program is intended to provide an enhanced level of operational capability, safety, and situational awareness and reduce the risk of injury. The UAS program will be utilized in a responsible, legal, and transparent manner with monthly usage data available on the Open Data Portal.

This dataset contains wireless communication signal data collected from an unmanned aerial vehicle (UAV) at different altitudes (40 m, 70 m, and 100 m). For the 40 m altitude, data was collected at varying sampling rates (5 MHz, 10 MHz, and 20 MHz), corresponding to bandwidths of 1.25 MHz, 2.5 MHz, and 5 MHz, respectively. The IQ recordings were made using USRP B210 devices at five fixed nodes (LW1-LW5). The dataset includes IQ samples, GPS coordinates, and received signal strength (RSS) values stored in SigMF format files. A Python script (example.py) is provided for data processing and visualization. Methods Trajectory and Altitudes: The UAV followed the same trajectory path at three different altitudes: 40 m, 70 m, and 100 m. Sampling Rates: For the 40 m altitude, data was collected using three different sampling rates: 5 MHz, 10 MHz, and 20 MHz, corresponding to bandwidths of 1.25 MHz, 2.5 MHz, and 5 MHz, respectively. Data Collection Intervals: To reduce data volume, the system collected data for 20 ms intervals every 100 ms. USRP B210 Devices: The IQ recordings were made using USRP B210 devices placed at the five fixed nodes (LW1-LW5). Each SigMF file contains IQ samples for two channels corresponding to the USRP's dual-channel configuration. GPS and Radio Measurements:

GPS coordinates (GPSx, GPSy, GPSz) were measured once per second, independent of the time at which the radio measurements were made. Radio measurements may have occurred more than once per second or not at exactly the same time as the GPS measurements. GPS and radio measurements are both time-stamped, and interpolation was used to calculate mX, mY, mZ values, which align the GPS data with the radio measurements based on their timestamps.

Folder Structure:

Each altitude (40 m, 70 m, 100 m) is represented by a folder. Within the 40 m folder, subfolders represent the three different sampling rates (5 MHz, 10 MHz, and 20 MHz). For each altitude and sampling rate combination, the dataset contains subfolders for five fixed nodes (LW1, LW2, LW3, LW4, and LW5). The locations of these nodes are detailed in the "LW1-5_locations.txt" file.

File Descriptions: SigMF Files:

results_3320000000_5000000_2024_07_15_12_26_01_248.sigmf-data: Contains IQ samples recorded at a frequency of 3320000000 Hz and a sampling rate of 5 MHz. The file contains two channels, one for each of the USRP B210 device's channels.

GPS Data:

gps_data.sigmf-data: Contains timestamped GPS coordinates of the UAV (GPSx, GPSy, GPSz), measured once per second.

Measurement Data:

measurement_rss_data.sigmf-data: Contains RSS data and interpolated position measurements (mX, mY, mZ) for each timestamp, with RSS1 for channel 1 and RSS2 for channel 2.

Python Script: example.py: This Python script demonstrates how to load and process the data from the SigMF files.

It uses libraries such as numpy, json, and matplotlib for loading data and plotting results. The script loads GPS metadata from gps_data.sigmf-meta and extracts position (GPSx, GPSy, GPSz) and timestamps. It also loads radio measurement data from measurement_rss_data.sigmf-meta and interpolates GPS data to align with radio measurements to compute positions (mX, mY, mZ) for further analysis. The script includes plotting functionalities to visualize the GPS trajectory and the corresponding RSS data over time.

The UAVs-based Forest Fire Database (UAVs-FFDB) encompasses four distinct classes: 1. Pre-evening Forest Condition 2. Evening Forest Condition 3. Pre-evening Fire Incident 4. Evening Fire Incident. The images were captured using UAVs equipped with Raspberry Pi Camera V2 technology in the forested areas surrounding Adana Alparslan Türkeş Science and Technology University, Adana, Turkey. This dataset is divided into two main components: original data (raw) and augmented data, each accompanied by an annotation file. The raw data comprises 1,653 images, while the augmented dataset contains 15,560 images. Below is the distribution of images across the four classes:

-Raw Data
Pre-evening Forest Condition = 222 Evening Forest Condition = 286
Pre-evening Fire Incident = 791 Evening Fire Incident = 354

-Augmented Data Pre-evening Forest Condition = 3,890 Evening Forest Condition = 3,890 Pre-evening Fire Incident = 3,890 Evening Fire Incident = 3,890

The data was collected with a Wingtra Gen II drone and a Sony RX1R II sensor. In total, 10 flights were conducted at different dates, both in summer and winter. A DSM, an orthophoto, a snow depth raster and the original drone images from every flight are available at a high resolution (10cm and 3cm, respectively).

Uav Palm Data Test

## Overview

Uav Palm Data Test is a dataset for object detection tasks - it contains Palms annotations for 500 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

This dataset contains drone RF signals that were recorded within the semi-anechoic chamber at the CISS department of the Royal Military Academy using an Ettus Research USRP X310. A high-speed 10 Gbit Ethernet cable connected the USRP to a computer for data acquisition. We recorded IQ data at a sampling rate of 100 MSps with a center frequency of 2.44 GHz, and an OmniLOG 70600 omnidirectional antenna was employed as the receiving antenna. Drones and remote controllers were positioned at a distance of seven meters from the receiving antenna. IQ samples from the USRP were recorded in binary format, and subsequently, we transformed these binary IQ vectors into complex signal vectors in Matlab, storing them as Mat files (version ‘-v7.3’).

Multispectral imagery data captured from Sequoia sensor from Parrot fixed-wing unmanned aerial vehicles (UAVs, or drones) by the participants of the Drones for Agriculture training course held in Kizimbani, Zanzibar, Tanzania, on August 20-22, 2018, in partnership with WeRobotics and Tanzania Flying Labs.

Unmanned Aerial Vehicles (UAV) provide increased access to unique types of urban imagery traditionally not available. Advanced machine learning and computer vision techniques when applied to UAV RGB image data can be used for automated extraction of building asset information and if applied to UAV thermal imagery data can detect potential thermal anomalies. However, these UAV datasets are not easily available to researchers, thereby creating a barrier to accelerating research in this area.

To assist researchers with added data to develop machine learning algorithms, we present UAVID3D (Unmanned Aerial Vehicle (UAV) Image Dataset of the Built Environment for 3D reconstruction). The raw images for our dataset were recorded with a Zenmuse XT2 visual (RGB) and a FLIR Tau 2 (thermal, https://flir.netx.net/file/asset/15598/original/) camera on a DJI Mavic 2 pro drone (https://www.dji.com/matrice-200-series). The thermal camera is factory calibrated. All data is organized and structured to comply with FAIR principles, i.e. being findable, accessible, interoperable, and reusable. It is publicly available and can be downloaded from the Zenodo data repository.

RGB images were recorded during UAV fly-overs of two different commercial buildings in Northern California. In addition, thermographic images were recorded during 2 subsequent UAV fly-overs of the same two buildings. UAV flights were recorded at flight heights between 60–80 m above ground with a flight speed of 1 m s and contain GPS information. All images were recorded during drone flights on May 10, 2021 between 8:45 am and 10:30 am and on May 19, 2021 between 2:15 pm and 4:30 pm. Outdoor air temperatures on these two days during the flights were between 78 and 83 degree fahrenheit and between 58 and 65 degree fahrenheit respectively.

For the RGB flights, UAV path was planned and captured using an orbital flight plan in PIX4D capture at normal flight speed and overlap angle of 10 degree. Thermal images were captured by manual flights approximately 5 m away from each building facade. Due to the high overlap of images, similarities from feature points identified in each image can be extracted to conduct photogrammetry. Photogrammetry allows estimation of the three-dimensional coordinates of points on an object in a generated 3D space involving measurements made on images taken with a high overlap rate. Photogrammetry can be used to create a 3D point cloud model of the recorded region. UAVID3D dataset is a series of compressed archive files totaling 21GB. Useful pipelines to process these images can be found at these two repositories https://github.com/LBNL-ETA/a3dbr, and https://github.com/LBNL-ETA/AutoBFE

This work was supported by the Assistant Secretary for Energy Efficiency and Renewable Energy, Building Technologies Program, of the U.S. Department of Energy under Contract No. DE-AC02-05CH11231.