Find research datasets worth reusing

opencc-by-4.0Sep 2024View details →

Hail Event on 2022-06-28 in Locarno-Monti (TI), Switzerland: Drone Photogrammetry Imagery, Mask R-CNN Model and Analysis Data of Hailstones

This hail data collection belongs to a drone hail survey performed on 2022-06-28 in Locarno-Monti (TI, Switzerland). The supercell reached the location around 07:50 UTC in the morning. Only one photogrammetry flight could be performed and thus no estimation of the hail melting process is available. The orthophoto is masked to ignore parts where detection of hail is unwanted.   Expert 1 (lai, mlainer), Expert 2 (jtm), Expert 3 (por, jportmann)

opencc-by-4.0Dec 2023View details →

Real-time black ice detection using YOLOX on drone

Detailed Info: https://github.com/hsh060824/blackice-drone-dataset   Dataset Type: Object Detection Dataset (with bounding boxes)   Overview Road safety during winter months remains a critical concern due to the elusive nature of black ice, a thin layer of ice that forms on road surfaces, making it challenging for drivers to identify and navigate safely. In an effort to address this issue, our research team at Cheongshim International Academy (CSIA) has conducted extensive studies on real-time black ice detection utilizing YOLOX, a state-of-the-art object detection algorithm, deployed on drones. As a significant contribution to the research community, we are pleased to share our meticulously curated image dataset, which encapsulates diverse scenarios and conditions representative of real-world black ice occurrences.   Background Black ice poses a significant threat to road safety, especially during winter, as it is often challenging for drivers to detect, leading to increased risks of accidents and hazardous road conditions. Our dataset aims to fill the gap in existing resources by providing a comprehensive collection of images showcasing various instances of black ice under different environmental conditions. The dataset covers diverse scenarios, including different lighting conditions, road surfaces, and black ice formations, making it a valuable resource for developing and testing robust black ice detection models.   Significances of the Dataset The significance of this dataset lies in its potential to advance the development of effective black ice detection algorithms. By sharing our dataset with the research community, we aim to facilitate the creation of more accurate and reliable models for real-time detection of black ice using drone technology. The dataset includes annotations in COCO format, providing detailed information about the location and characteristics of black ice instances in each image.   Categorization In our pursuit of advancing the field of computer vision and contributing to ongoing research endeavors, we proudly introduce three distinct image datasets meticulously curated by our research team. These datasets, categorized as "White," "Black," and "Outdoors (OD)," cater to unique scenarios and are designed to fuel the development of specialized models addressing specific challenges in visual recognition.   White Dataset:  <ul> <li>Composition: This dataset comprises 413 images, each meticulously annotated with an average of 1.1 annotations per image, depicting the unique optical characteristics of black ice.</li> <li>Properties: The average proportion of instance pixel area is 3.16%, emphasizing the subtlety of the black ice formations. The average image brightness is measured at 149.358.</li> <li>Capture Environment: The images were taken in controlled indoor laboratory conditions, ensuring consistency and repeatability.</li> <li>Creation Method: The dataset was generated by cooling asphalt samples in a freezer to temperatures ranging from -4°C to -20°C. Subsequently, 4°C water was sprayed onto the sample surfaces, creating black ice. The dataset captures the optical properties of black ice, showcasing its interaction with light.</li> <li>Significance: Valuable for highlighting the optical characteristics of black ice, enhancing model accuracy in well-lit scenarios.</li> </ul>   Black Dataset:  <ul> <li>Composition: This dataset comprises 814 images, with a detailed annotation structure averaging 3.5 annotations per image, showcasing the challenges of recognition in low-light conditions.</li> <li>Properties: The average proportion of instance pixel area is notably higher at 12.37%, reflecting the complex and varied formations of black ice. The average image brightness is measured at 123.028.</li> <li>Capture Environment: Similar to the White Dataset, images were captured in a controlled indoor laboratory environment. Asphalt pelt was placed under the black iced asphalt pieces to replicate realistic scenarios.</li> <li>Creation Method: The dataset creation involved the same process of cooling asphalt samples, followed by spraying water to create black ice. To simulate real-world conditions, asphalt pelt was used as a background, and various shapes of black ice were randomly placed in each image.</li> <li>Significance: Realistic emulation of black ice using backgrounds made up of asphalt pelts, providing essential drark images for robust model training.</li> </ul>   Outdoor (OD) Dataset <ul> <li>Composition: This dataset is the most extensive, consisting of 1624 images, with an average of 1.5 annotations per image, capturing the challenges of recognizing black ice in outdoor winter conditions.</li> <li>Properties: The average proportion of instance pixel area is 12.34%, mirroring the complexity of real-world outdoor scenarios. The average image brightness is significantly lower at 56.575.</li> <li>Capture Environment: Unlike the indoor datasets, the OD dataset was captured outdoors in winter conditions where black ice naturally forms.</li> <li>Creation Method: Black ice was created on the asphalt road of Cheongsim International High School by spraying +4°C water onto the surface. DJI Tello's built-in camera was used for capturing images from various angles, simulating drone-like perspectives. This dataset is designed to closely replicate real-world scenarios, providing a valuable resource for training models for outdoor applications.</li> <li>Significance: Represents real-world outdoor scenarios, offering a unique perspective for developing models capable of handling diverse and challenging conditions.</li> </ul>   Cameras:  <ul> <li>iPhone SE2 (Apple, California)</li> <li>iPhone SE3 (Apple, California)</li> <li>iPhone 12 (Apple, California)</li> <li>iPhone 14 Pro (Apple, California)</li> <li>Q9 (LG Electronics, Seoul, Korea)</li> <li>V30 (LG Electronics, Seoul, Korea)</li> <li>Tello (DJI, ShenZhen, China)</li> </ul>

opencc-by-4.0Aug 2022View details →

Thermal Bridges on Building Rooftops - Hyperspectral (RGB + Thermal + Height) drone images of Karlsruhe, Germany, with thermal bridge annotations

Overview: The dataset of Thermal Bridges on Building Rooftops (TBBR dataset) consists of annotated combined RGB and thermal drone images with a height map. All images were converted to a uniform format of 3000x4000 pixels, aligned, and cropped to 2680x3370 to remove empty borders. See the "Usage" section below for details about the stored formats made available here. The raw images for our dataset were recorded with a normal (RGB) and a FLIR-XT2 (thermal) camera on a DJI M600 drone. They show six large building blocks of around 20 buildings per block recorded in the city centre of the German city Karlsruhe east of the market square. Because of a high overlap rate of the images, the same buildings are on average recorded from different angles in different images about 20 times. All images were recorded during a drone flight on March 19, 2019 from 7 a.m. to 8 a.m. At this time, temperatures were between 3.78 ° C and 4.97 ° C, humidity between 80% and 98%. There was no rain on the day of the flight, but there was 2.3mm/m² 48 hours beforehand. For recording the thermographic images an emissivity of 1.0 was set. The global radiation during this period was between 38.59 W / m² and 120.86 W / m². No direct sunlight can be seen visually on any of the recordings. The dataset contains 926 images with a total of 6,927 annotations of thermal bridges on rooftops, split into train and test subsets with 723 (5,614) and 203 (1,313) images (annotations), respectively. The annotations only include thermal bridges that are visually identifiable with the human eye. Because of the aforementioned image overlap, each thermal bridge is annotated multiple times from different angles. For the annotation of the thermal images the image processing program VGG Image Annotator from the Visual Geometry Group, version 2.0.10, was used. The thermal bridge annotations are outlined with polygon shapes. These polygon lines were placed as close as possible but outside the area of significant temperature increase. If a detected thermal bridge was partially covered by another building component located in the foreground, the thermal bridge was also marked across the covering in case of minor coverings. Adjacent thermal bridges, which affect different rooftop components, were annotated separately. For example, a window with poor insulation of the window reveal located in the area of a poorly insulated roof is annotated individually. There is no overlap between annotated areas. While each image contains annotations, they also include thermal bridges present that are not annotated. Usage: Each compressed archive file represents one of the six flight paths. For the related publication the final path (Flug1_105Media) was used as a hold-out test sample. The archives contain Numpy files (one per image) of shape (2680, 3370, 5), where the final dimension is the colour channel in the format [B, G, R, Thermal, Height]. Archives were compressed using <a href="https://facebook.github.io/zstd/">ZStandard</a> compression. They can be decompressed in a terminal by running e.g. <pre><code class="language-bash">tar -I zstd -xvf Flug1_105Media.tar.zst</code></pre> these will be decompressed into the file structure: <pre><code>images/ └── Flug1_105Media/ └── DJI_0004_R.npy └── DJI_0006_R.npy └── ...</code></pre> Corresponding annotations are provided in the COCO JSON format. There is one file for training (Flug1_100Media - Flug1_104Media blocks) and one for test (Flug1_105Media block). They contain a single class (thermal bridge) and expect the folder structure shown below. Note: The annotation files contain relative paths to numpy files, in case of problems please convert to absolute paths (i.e. insert the containing directory before each file path in the JSON annotation files). We provide the <a href="https://github.com/Helmholtz-AI-Energy/TBBRDet">TBBRDet software</a> which includes a dataloader and dataset inspection tools which make use of the <a href="https://github.com/facebookresearch/detectron2">Detectron2</a> and <a href="https://github.com/open-mmlab/mmdetection">MMDetection</a> libraries. We recommend the following folder structure for use: <pre><code>├── train/ │ ├── Flug1_100-104Media_coco.json │ └── images/ │ ├── Flug1_100Media/ │ │ ├── DJI_XXXX_R.npy │ │ └── ... │ ├── ... │ └── Flug1_104Media/ │ ├── DJI_XXXX_R.npy │ └── ... └── test/ ├── Flug1_105Media_coco.json └── images/ └── Flug1_105Media/ ├── DJI_XXXX_R.npy └── ...</code></pre> Metadata: The experimental metadata was structured with the Spatio Temporal Asset Catalog (STAC) specification family. This specification provides a standardized way for describing geospatial assets. It defines related JSON object types of Item, Catalog, and Catalog, extending on Collection as the basis. One STAC Collection JSON object provides information about the recorded images and the environmental conditions during recordings. It also contains information about the overall bounding box of the entire area in which images were recorded. This object links to related STAC Item JSON objects containing information about the recorded city blocks and the cameras. The objects for the city blocks contain the GeoJSON geometry of the respective block and the corresponding bounding box. The objects containing the camera information are based on an existing STAC extension for camera related metadata. Metadata of the archived NumPy files for each image was structured using the Data Package schema from the Frictionless Standards. This standard describes a collection of data files. Therefore, metadata about all containerized NumPy files of the six flight paths (Flug1_100Media - Flug1_104Media blocks and Flug1_105Media block) is provided within a JSON-based file. Note that camera1 corresponds to the RGB camera and camera2 the thermal. FAIR Digital Objects: All files are represented in a standardized way as FAIR Digital Objects (FAIR DOs) to enable machine actionable decisions on the data in spirit of the FAIR principles. Persistent Identifier (PID): Persistent Identifiers (PIDs) are resolvable with the <a href="https://hdl.handle.net/">Handle.Net Registry (HNR)</a>. <table> <thead> <tr> <th scope="col">File</th> <th scope="col">Persistent Identifier (PID)</th> </tr> </thead> <tbody> <tr> <td>Flug1_100-104Media_coco.json</td> <td>21.11152/6ea60288-d895-414e-80c0-26c9fdd662b2</td> </tr> <tr> <td>Flug1_105Media_coco.json</td> <td>21.11152/58d43ddc-5e29-4980-8675-ae579b50a1e2</td> </tr> <tr> <td>Flug1_100.tar.zst</td> <td>21.11152/6858a0b5-cc60-40e9-afef-8c2dd8b35e8e</td> </tr> <tr> <td>Flug1_101.tar.zst</td> <td>21.11152/e670f510-7e00-4d3a-9b90-3bac7a7c069e</td> </tr> <tr> <td>Flug1_102.tar.zst</td> <td>21.11152/3ab9f444-05f6-445e-a691-62fae4021bea</td> </tr> <tr> <td>Flug1_103.tar.zst</td> <td>21.11152/365fd8cf-8e86-41b8-9d0e-b816fdd01d29</td> </tr> <tr> <td>Flug1_104.tar.zst</td> <td>21.11152/041a6111-644a-4617-afb3-3c421a88e8e3</td> </tr> <tr> <td>Flug1_105.tar.zst</td> <td>21.11152/f48bf4e7-3879-4216-8f64-45a060b8f658</td> </tr> <tr> <td>Flug1_100-105_frictionless_standards.json</td> <td>21.11152/7b58b3b5-75eb-4417-ac4d-abe025e159f6</td> </tr> <tr> <td>Flug1_collection_stac_spec.json</td> <td>21.11152/ba370aa3-6422-428c-9ff7-c2ef429df603</td> </tr> <tr> <td>Flug1_100_stac_spec.json</td> <td>21.11152/09cb76fc-b8cb-4116-a22a-68c5bdfa77b0</td> </tr> <tr> <td>Flug1_101_stac_spec.json</td> <td>21.11152/24a55398-b96b-43dd-b0fb-cd8ce302c7ce</td> </tr> <tr> <td>Flug1_102_stac_spec.json</td> <td>21.11152/721234ac-4b5a-4d02-9944-82a08ef2db35</td> </tr> <tr> <td>Flug1_103_stac_spec.json</td> <td>21.11152/ebaeb5bc-0514-47c9-bcd2-98f0253843d8</td> </tr> <tr> <td>Flug1_104_stac_spec.json</td> <td>21.11152/9854677c-77c5-4a0b-916b-57dd9ec20198</td> </tr> <tr> <td>Flug1_105_stac_spec.json</td> <td>21.11152/cfd0fc0e-f5ea-464e-a57f-28e882924860</td> </tr> <tr> <td>Flug1_camera1_stac-spec.json</td> <td>21.11152/976fcf28-f924-4a21-b53d-5d054ad8198d</td> </tr> <tr> <td>Flug1_camera2_stac-spec.json</td> <td>21.11152/37833c54-1d36-42e4-858d-831447122863</td> </tr> </tbody> </table>

VHR orthomosaic imageries produced by dedicated drone flight campaigns over Lithuania (2021-2022) - Vilnius -AOI 1, Sub-region 1

In the context of the EU-funded project DIONE (No. 870378), targeted drone flight campaigns were conducted in determined Areas of Interest (AOIs) in the Lithuanian territory as a complementary source of information to the spaceborne Earth Observation (EO) open-accessed data. Such an activity attempted to overcome the limited capabilities of EO coarse resolution data to identify small-scale features alongside the agricultural fields, such as the non-productive Ecological Focus Areas (EFAs) and overall to enhance the quality and accuracy (1m or less) of the estimated Land Cover/Land Use elements. The dataset is in fact a collection of drone orthomosaic images delivered in GeoTIFF data format, which were acquired from the drone flight missions over the first subregion of the first AOI located near the capital of Lithuania, (Vilnius). For each area, four flight campaigns were scheduled and conducted on the following dates:      <ul> <li>1st flight: 24-27/5/2021</li> <li>2nd flight: 26-29/7/2021</li> <li>3rd flight: 13-16/9/2021</li> <li>4th flight: 25-28/8/2022</li> </ul>

VHR orthomosaic imageries produced by dedicated drone flight campaigns over Lithuania (2021-2022) - Vilnius -AOI 2

In the context of the EU-funded project DIONE (No. 870378), targeted drone flight campaigns were conducted in determined Areas of Interest (AOIs) in the Lithuanian territory as a complementary source of information to the spaceborne Earth Observation (EO) open-accessed data. Such an activity attempted to overcome the limited capabilities of EO coarse resolution data to identify small-scale features alongside the agricultural fields, such as the non-productive Ecological Focus Areas (EFAs) and overall to enhance the quality and accuracy (1m or less) of the estimated Land Cover/Land Use elements. The dataset is in fact a collection of drone orthomosaic images delivered in GeoTIFF data format, which were acquired from the drone flight missions over the second AOI located near the capital of Lithuania, (Vilnius). For each area, four flight campaigns were scheduled and conducted on the following dates:      <ul> <li>1st flight: 24-27/5/2021</li> <li>2nd flight: 26-29/7/2021</li> <li>3rd flight: 13-16/9/2021</li> <li>4th flight: 25-28/8/2022</li> </ul>

VHR orthomosaic imageries produced by dedicated drone flight campaigns over Cyprus (2021-2022) - Choirokoitia region

In the context of the EU-funded project DIONE (No. 870378), targeted drone flight campaigns were conducted in determined Areas of Interest (AOIs) in the Cypriotic territory as a complementary source of information to the spaceborne Earth Observation (EO) open-accessed data. Such an activity attempted to overcome the limited capabilities of EO coarse resolution data to identify small-scale features alongside the agricultural fields, such as the non-productive Ecological Focus Areas (EFAs) and overall to enhance the quality and accuracy (1m or less) of the estimated Land Cover/Land Use elements. The dataset is in fact a collection of drone orthomosaic images delivered in GeoTIFF data format, which were acquired from the drone flight missions over one of the two determined locations in Cyprus (e.g. Choirokoitia). For each area, four flight campaigns were scheduled and conducted on the following dates:      <ul> <li>1st flight: 29/3/2021- 1/4/2021</li> <li>2nd flight: 30/8/2021-2/9/2021</li> <li>3rd flight: 29/11/2021-03/12/2021</li> <li>4th flight: 17-20/5/2022</li> </ul>

VHR orthomosaic imageries produced by dedicated drone flight campaigns over Cyprus (2021-2022) - Akaki region

In the context of the EU-funded project DIONE (No. 870378), targeted drone flight campaigns were conducted in determined Areas of Interest (AOIs) in the Cypriotic territory as a complementary source of information to the spaceborne Earth Observation (EO) open-accessed data. Such an activity attempted to overcome the limited capabilities of EO coarse resolution data to identify small-scale features alongside the agricultural fields, such as the non-productive Ecological Focus Areas (EFAs) and overall to enhance the quality and accuracy (1m or less) of the estimated Land Cover/Land Use elements. The dataset is in fact a collection of drone orthomosaic images delivered in GeoTIFF data format, which were acquired from the drone flight missions over one of the two determined locations in Cyprus (e.g. Akaki). For each area, four flight campaigns were scheduled and conducted on the following dates:      <ul> <li>1st flight: 29/3/2021- 1/4/2021</li> <li>2nd flight: 30/8/2021-2/9/2021</li> <li>3rd flight: 29/11/2021-03/12/2021</li> <li>4th flight: 17-20/5/2022</li> </ul>

VHR orthomosaic imageries produced by dedicated drone flight campaigns over Lithuania (2021-2022) - Vilnius -AOI 1, Sub-region 2

In the context of the EU-funded project DIONE (No. 870378), targeted drone flight campaigns were conducted in determined Areas of Interest (AOIs) in the Lithuanian territory as a complementary source of information to the spaceborne Earth Observation (EO) open-accessed data. Such an activity attempted to overcome the limited capabilities of EO coarse resolution data to identify small-scale features alongside the agricultural fields, such as the non-productive Ecological Focus Areas (EFAs) and overall to enhance the quality and accuracy (1m or less) of the estimated Land Cover/Land Use elements. The dataset is in fact a collection of drone orthomosaic images delivered in GeoTIFF data format, which were acquired from the drone flight missions over the second subregion of the first AOI located near the capital of Lithuania, (Vilnius). For each area, four flight campaigns were scheduled and conducted on the following dates:      <ul> <li>1st flight: 24-27/5/2021</li> <li>2nd flight: 26-29/7/2021</li> <li>3rd flight: 13-16/9/2021</li> <li>4th flight: 25-28/8/2022</li> </ul>

opencc-by-4.0Dec 2017View details →

Drone-based photogrammetric survey raw data from ESA PANGAEA-X 2017 planetary analogue campaign - Data collected on 2017-11-19

Drone-based photogrammetric survey data from ESA PANGAEA-X 2017 planetary analogue campaign. Data were collected in the framework of the ESA PANGAEA-X testing campaign held in November 2017: We acknowledge ESA for organising the campaign and providing scientific and logistic assistance on site. The authors would like also to thank the Geopark of Lanzarote, the touristic center of Cueva de Los Verdes, the Cabildo of Lanzarote, the National Park of Timanfaya and the IGEO-CSIC-UCM for providing the necessary permits. Data collected on 2017-11-19 during an aerial survey with a DJI Phantom 4 - data from AGPA experiments (AGPA-D) see http://www.agpa-project.eu

opencc-by-4.0Oct 2024View details →

Data for estimating spruce tree health using drone-based RGB and multispectral imagery

The dataset contains multispectral and RGB orthomosaics (.tif), and photogrammetric point clouds (.laz) of four study areas (about 25 ha each), where bark beetle-related decline of Norway spruce has been observed in Helsinki, Finland. The filenames refer to Area 1 (Männikkötie), Area 2 (Maunulanmaja), Area 3 (Hakuninmaa), and Area 4 (Paloheinä), described in detail in Junttila et al. 2022. Multispectral Imagery Provides Benefits for Mapping Spruce Tree Decline Due to Bark Beetle Infestation When Acquired Late in the Season, Remote Sensing 14(4), 909: <a href="https://doi.org/10.3390/rs14040909">https://doi.org/10.3390/rs14040909</a>  The image data was acquired between 11th and 14th September 2020. RE = Red-Edge M multispectral data RGB = RGB data (Phantom 4 Pro) Altum = Altum multispectral data The ground sampling distances (GSD) were approximately 3 cm, 5 cm, and 8 cm for RGB, Altum, and RedEdge, respectively. The field reference data file contains 556 geolocated trees assessed in the field (between 11.9. and 17.9.2020), of which 203 were dead and 353 were alive. The data is in polygon format, representing the crown delineation done during the data processing. The file includes tree heights estimated from airborne laser scanning data, dbh (for a subset of trees), discoloration, defoliation, resin flow, bark structural damage, and canopy size estimates. More details are in the journal article mentioned above. Key for Field Reference: Z = tree height dbh = diameter-at-breast-height (cm) vari = Discoloration (score 0-5) harsu = Defoliation (score 0-4) pihka = Resin flows (score 0-2) runko = Stem/bark structural damage (score 0-2) latvus = Significantly decreased canopy size (score 0-1)

opencc-by-4.0Oct 2021View details →

Data from: Complex population structure and haplotype patterns in Western Europe honey bee from sequencing a large panel of haploid drones

This vcf file contains 7.023.689 SNPs and 870 honey bee samples, as described in the paper "Complex population structure and haplotype patterns in Western Europe honey bee from sequencing a large panel of haploid drones" by Wragg et al., available at https://doi.org/10.1101/2021.09.20.460798 as preprint. Eight hundred and seventy haploid drone samples from several honey bee subspecies hybrids were sequenced and aligned to the HAv3.1 reference genome. Sequence read alignment and genotyping quality filters were used to obtain a selection of 7.023.689 high-quality SNPs. The file Diversity_Study_629_Samples.txt corresponds to the 629 unique samples that were used for the diversity study described in the paper and can be used to recreate the restricted diversity dataset using bcftools or an equivalent software. Having sequenced haploid drones, heterozygous SNPs resulting from duplicated regions could be filtered out and the data is phased.

opencc-by-4.0Oct 2021View details →

Supplement for Drone-based magnetic and multispectral surveys to develop a 3D model for mineral exploration at Qullissat, Disko Island, Greenland

Supplement to Jackisch et al., 2021: Drone-based magnetic and multispectral surveys to develop a 3D model for mineral exploration at Qullissat, Disko Island, Greenland. <a href="https://se.copernicus.org/articles/13/793/2022/se-13-793-2022.html">https://se.copernicus.org/articles/13/793/2022/se-13-793-2022.html</a> Data set contains 3D model in dxf file, additional images, selected handheld spectra. Publication summary: We integrate UAS-based magnetic and remote sensing mineral exploration data with legacy exploration data of a Ni-Cu-PGE prospect on Disko Island, West Greenland. The basalt unit has a complex magnetization, and we use a 3D magnetic vector inversion on the UAS magnetics to estimate magnetic properties and spatial dimensions of the mineralized unit. Our 3D modelling reveals a horizontal sheet and a strong remanent magnetization component. We highlight the advantage of UAS in rugged terrain.

opencc-by-4.0Nov 2022View details →

Hyperspectral (RGB + Thermal) drone images of Karlsruhe, Germany - Raw images for the Thermal Bridges on Building Rooftops (TBBR) dataset

Overview: This repository contains the raw images for the dataset of <a href="https://doi.org/10.5281/zenodo.4767771">Thermal Bridges on Building Rooftops (TBBR) dataset</a>. This dataset contains 5696 drone images (2848 RGB and 2848 thermal) of building rooftops, recorded with a normal (RGB) and a FLIR-XT2 (thermal) camera on a DJI M600 drone. They show six large building blocks of around 20 buildings per block recorded in the city centre of the German city Karlsruhe east of the market square. Because of a high overlap rate of the images, the same buildings are on average recorded from different angles in different images about 20 times. All images were recorded during a drone flight on March 19, 2019 from 7 a.m. to 8 a.m. At this time, temperatures were between 3.78 ° C and 4.97 ° C, humidity between 80% and 98%. There was no rain on the day of the flight, but there was 2.3mm/m² 48 hours beforehand. For recording the thermographic images an emissivity of 1.0 was set. The global radiation during this period was between 38.59 W / m² and 120.86 W / m². No direct sunlight can be seen visually on any of the recordings. Usage: Each zip archive file represents one of the six drone flight paths. The archives contain JPG files of size 4000x3000 pixels (RGB) and 640x512 (Thermal), separated into individual directories for RGB and Thermal: <pre><code>├── Flug_100/ │ ├── RGB/ │ │ ├── DJI_0004.jpg │ │ ├── DJI_0006.jpg │ │ └── ... │ └── Thermal/ │ ├── DJI_0003_R.JPG │ ├── DJI_0005_R.JPG │ └── ... ├── Flug_101/ │ ├── RGB/ │ │ ├── DJI_0001.jpg │ │ ├── DJI_0003.jpg │ │ └── ... │ └── Thermal/ │ ├── DJI_0000_R.JPG │ ├── DJI_0002_R.JPG │ └── ... └── ...</code></pre> File Numbering/Naming Scheme: The pairs of RGB + Thermal images follow the simple numbering scheme of: RGB = Thermal + 1. For example, DJI_0003_R.jpg and DJI_0004.JPG are the matching Thermal and RGB images, respectively, that can be merged to form a single hyperspectral drone image. To perform the merging, we recommend using the merge_image_layers.py script provided by the associated <a href="https://github.com/Helmholtz-AI-Energy/TBBRDet">TBBRDet software</a> (see the scripts/alignment/ directory). For convenience, we have provided a CSV listing all annotated images in the <a href="https://doi.org/10.5281/zenodo.4767771">Thermal Bridges on Building Rooftops (TBBR) dataset</a>. The CSV format is as follows: <pre><code>Flight,RGB,Thermal Flug_100,DJI_0048.jpg,DJI_0047_R.JPG Flug_100,DJI_0050.jpg,DJI_0049_R.JPG ...</code></pre>

opencc-by-4.0Feb 2023View details →

Drone onboard multi-modal sensor dataset

Drone onboard multi-modal sensor dataset : This dataset contains timeseries data from numerous drone flights. Each flight record has a unique identifier (uid) and a timestamp  indicating when the flight occurred. The drone's position is represented by the coordinates (position_x, position_y, position_z) and  altitude. The orientation of the drone is represented by the quaternion (orientation_x, orientation_y, orientation_z, orientation_w). The  drone's velocity and angular velocity are represented by (velocity_x, velocity_y, velocity_z) and (angular_x, angular_y, angular_z) respectively. The linear acceleration of the drone is represented by (linear_acceleration_x, linear_acceleration_y, linear_acceleration_z). In addition to the above, the dataset also contains information about the battery voltage (battery_voltage) and current (battery_current) and  the payload attached. The payload information indicates if the drone operated with an embdded device attached (nvidia jetson), various sensors,  and a solid-state weather station (trisonica). The dataset also includes annotations for the current state of the drone, including IDLE_HOVER, ASCEND, TURN, HMSL and  DESCEND. These states can be used for classification to identify the current state of the drone. Furthermore, the labeled dataset can be used for predicting the trajectory of the drone using multi-task learning. For the annotation, we look at the change in position_x, position_y, position_z and yaw. Specifically, if the position_x, position_y changes, it means that the drone moves in a horizontal straight line, if the position_z changes, it means that the drone performs ascending or descending (depends on whether it increases or decreases), if the yaw changes, it means that the drone performs a turn and finally if any of the above features do not change, it means the drone is in idle or hover mode. In addition to the features already mentioned, this dataset also includes data from various sensors including a weather station and an Inertial Measurement Unit (IMU). The weather station provides information about the weather conditions during the flight. This information includes, wind speed, and wind angle. These weather variables could be important factors that could influence the flight of the drone and battery consumption. The IMU is a sensor that measures the drone's acceleration, angular velocity, and magnetic field. The accelerometer provides information about the drone's linear acceleration, while the gyroscope provides information about the drone's angular velocity. The magnetometer measures the Earth's magnetic field, which can be used to determine the drone's orientation. Field deployments were performed in order to collect empirical data using a specific type of drone, specifically a DJI Matrice 300 (M300).  The M300 is equipped with advanced sensors and flight control systems, which can provide high-precision flight data. The flights were designed  to cover a range of flight patterns, which include triangular flight patterns, square flight patterns, polygonal flight pattern,  and random flight patterns. These flight patterns were chosen to represent a variety of different flight scenarios that could be encountered  in real-world applications. The triangular flight pattern consists of the drone flying in a triangular path with a fixed altitude.  The square flight pattern involves the drone flying in a square path with a fixed altitude. The polygonal flight pattern consists of the drone  flying in a polygonal path with a fixed altitude, and the random flight pattern involves the drone flying in a random path with a fixed altitude. Overall,  this dataset contains a rich set of flight data that can be used for various research purposes, including developing and testing algorithms for  drone control, trajectory planning, and machine learning.

Orthophoto & DEM (MNE) issues d'images drone, UAV, Iot, Madagascar - 20230502 - 02_1

"Ce jeu de données présente les résultats des traitements photogrammétriques d'images de drone DJI Mavic 2 Pro UAV acquises sur le site de Iot, Madagascar à la date suivante : 20230502. Les vols ont été réalisés en partenariat avec l'IH.SM dans le but de créer des modèles numériques d'élévations pour cartographier l'écosystème marin. Le paramétrage du logiciel OpenDroneMap est partagé pour permettre la reproductibilité ou l'amélioration des traitements proposés: [ { 'name': 'orthophoto-resolution', 'value': 1 }, { 'name': 'auto-boundary', 'value': true }, { 'name': 'dem-resolution', 'value': '2.0' }, { 'name': 'dsm', 'value': true } ] Le dépôt est composé des éléments suivants: - 00_: Planche d'aperçu des images - DCIM.zip: Images brutes issues du drone - GPS.zip: Geopackage contenant l'emprise du survol ainsi que la géolocalisation des images accompagnées de leurs miniatures dans la table d'attribut en base64 - METADATA.zip: Métadonnées au format ISO19115, Rapports avec miniatures des images de drone (dossier tb) et statistiques de vols. - PROCESSED_DATA.zip: Orthophoto, DEM, nuages de points, ... Arborescence d'origine: │ └─ 20230502_MDG-iot_UAV-02_1 │-------- └─ DCIM │-------- └─ GPS │-------- └─ METADATA │---------------- └─ tb │-------- └─ PROCESSED_DATA Informations de survol: - Camera model and parameters: Make: Hasselblad Model: L1D-20c Width: 5472 Height: 3648 Focal: 28 WhiteBalance: Manual ExposureMode: Auto Exposure ColoSpace: sRGB EV: -0.7 MeteringMode: CenterWeightedAverage Camera Pitch: -89.90 - Survey informations: No Images: 303 Median height: 256 meters Survey area: 141.79 hectares Survey from: 2023:05:02 16:10:31 to: 2023:05:02 16:50:41 "

Orthophoto & DEM (MNE) issues d'images drone, UAV, Nosyve, Madagascar - 20230430 - 02_1

"Ce jeu de données présente les résultats des traitements photogrammétriques d'images de drone DJI Mavic 2 Pro UAV acquises sur le site de Nosyve, Madagascar à la date suivante : 20230430. Les vols ont été réalisés en partenariat avec l'IH.SM dans le but de créer des modèles numériques d'élévations pour cartographier l'écosystème marin. Le paramétrage du logiciel OpenDroneMap est partagé pour permettre la reproductibilité ou l'amélioration des traitements proposés: [ { 'name': 'orthophoto-resolution', 'value': 1 }, { 'name': 'auto-boundary', 'value': true }, { 'name': 'dem-resolution', 'value': '2.0' }, { 'name': 'dsm', 'value': true } ] Le dépôt est composé des éléments suivants: - 00_: Planche d'aperçu des images - DCIM.zip: Images brutes issues du drone - GPS.zip: Geopackage contenant l'emprise du survol ainsi que la géolocalisation des images accompagnées de leurs miniatures dans la table d'attribut en base64 - METADATA.zip: Métadonnées au format ISO19115, Rapports avec miniatures des images de drone (dossier tb) et statistiques de vols. - PROCESSED_DATA.zip: Orthophoto, DEM, nuages de points, ... Arborescence d'origine: │ └─ 20230430_MDG-nosyve_UAV-02_1 │-------- └─ DCIM │-------- └─ GPS │-------- └─ METADATA │---------------- └─ tb │-------- └─ PROCESSED_DATA Informations de survol: - Camera model and parameters: Make: Hasselblad Model: L1D-20c Width: 5472 Height: 3648 Focal: 28 WhiteBalance: Manual ExposureMode: Auto Exposure ColoSpace: sRGB EV: -0.7 MeteringMode: CenterWeightedAverage Camera Pitch: -85.00 - Survey informations: No Images: 467 Median height: 75 meters Survey area: 76.32 hectares Survey from: 2023:04:30 09:34:58 to: 2023:04:30 09:56:17 "

Orthophoto & DEM (MNE) issues d'images drone, UAV, Sarodrano, Madagascar - 20230505 - 02_1

"Ce jeu de données présente les résultats des traitements photogrammétriques d'images de drone DJI Mavic 2 Pro UAV acquises sur le site de Sarodrano, Madagascar à la date suivante : 20230505. Les vols ont été réalisés en partenariat avec l'IH.SM dans le but de créer des modèles numériques d'élévations pour cartographier l'écosystème marin. Le paramétrage du logiciel OpenDroneMap est partagé pour permettre la reproductibilité ou l'amélioration des traitements proposés: [ { 'name': 'orthophoto-resolution', 'value': 1 }, { 'name': 'auto-boundary', 'value': true }, { 'name': 'dem-resolution', 'value': '2.0' }, { 'name': 'dsm', 'value': true } ] Le dépôt est composé des éléments suivants: - 00_: Planche d'aperçu des images - DCIM.zip: Images brutes issues du drone - GPS.zip: Geopackage contenant l'emprise du survol ainsi que la géolocalisation des images accompagnées de leurs miniatures dans la table d'attribut en base64 - METADATA.zip: Métadonnées au format ISO19115, Rapports avec miniatures des images de drone (dossier tb) et statistiques de vols. - PROCESSED_DATA.zip: Orthophoto, DEM, nuages de points, ... Arborescence d'origine: │ └─ 20230505_MDG-sarodrano_UAV-02_1 │-------- └─ DCIM │-------- └─ GPS │-------- └─ METADATA │---------------- └─ tb │-------- └─ PROCESSED_DATA Informations de survol: - Camera model and parameters: Make: Hasselblad Model: L1D-20c Width: 5472 Height: 3648 Focal: 28 WhiteBalance: Manual ExposureMode: Auto Exposure ColoSpace: sRGB EV: -0.7 MeteringMode: Average Camera Pitch: -89.90 - Survey informations: No Images: 177 Median height: 155 meters Survey area: 59.52 hectares Survey from: 2023:05:05 07:03:19 to: 2023:05:05 07:17:41 "

Orthophoto & DEM (MNE) issues d'images drone, UAV, Iot, Madagascar - 20230503 - 02_1

"Ce jeu de données présente les résultats des traitements photogrammétriques d'images de drone DJI Mavic 2 Pro UAV acquises sur le site de Iot, Madagascar à la date suivante : 20230503. Les vols ont été réalisés en partenariat avec l'IH.SM dans le but de créer des modèles numériques d'élévations pour cartographier l'écosystème marin. Le paramétrage du logiciel OpenDroneMap est partagé pour permettre la reproductibilité ou l'amélioration des traitements proposés: [ { 'name': 'orthophoto-resolution', 'value': 1 }, { 'name': 'auto-boundary', 'value': true }, { 'name': 'dem-resolution', 'value': '2.0' }, { 'name': 'dsm', 'value': true } ] Le dépôt est composé des éléments suivants: - 00_: Planche d'aperçu des images - DCIM.zip: Images brutes issues du drone - GPS.zip: Geopackage contenant l'emprise du survol ainsi que la géolocalisation des images accompagnées de leurs miniatures dans la table d'attribut en base64 - METADATA.zip: Métadonnées au format ISO19115, Rapports avec miniatures des images de drone (dossier tb) et statistiques de vols. - PROCESSED_DATA.zip: Orthophoto, DEM, nuages de points, ... Arborescence d'origine: │ └─ 20230503_MDG-iot_UAV-02_1 │-------- └─ DCIM │-------- └─ GPS │-------- └─ METADATA │---------------- └─ tb │-------- └─ PROCESSED_DATA Informations de survol: - Camera model and parameters: Make: Hasselblad Model: L1D-20c Width: 5472 Height: 3648 Focal: 28 WhiteBalance: Manual ExposureMode: Auto Exposure ColoSpace: sRGB EV: -0.7 MeteringMode: CenterWeightedAverage Camera Pitch: -90.00 - Survey informations: No Images: 299 Median height: 148 meters Survey area: 132.44 hectares Survey from: 2023:05:03 07:06:46 to: 2023:05:03 07:48:00 "