Find research datasets worth reusing

opencc-by-4.0Jan 2022View details →

mDRONES4rivers-project: Portfolios of classification results, UAV and gyrocopter data of project sites situated in riparian zones along federal waterways in Germany with focus on the Rhine River, Germany

Spatially and temporally high-resolution data was acquired with the aid of multispectral sensors mounted on UAV and a gyrocopter platform for the purpose of classification. The work was part of the research and development project &bdquo;Modern sensors and airborne remote sensing for the mapping of vegetation and hydromorphology along Federal waterways in Germany“ (mDRONES4rivers) in cooperation of the German Federal Institute of Hydrology (BfG), Geocoptix GmbH, Hochschule Koblenz und JB Hyperspectral Devices.  Within the project period (2019-2022) data was collected at different sites situated in Germany along the Rivers Rhine and Oder. All published data produced within the project can be found by searching for the keyword ‘mDRONES4rivers‘.  In this dataset, the following portfolios of classifications, UAS and gyrocopter data of project sites situated in riparian zones along federal waterways in Germany with focus on the Rhine River are available for download: •             Multispectral orthophotos produced with the aid of UAS (PDF, Detailed description of sensors and data acquisition procedure; abbreviation: MS_ORTHO) •             RGB-orthophotos and digital surface models produced with the aid of UAS (PDF, Detailed description of sensors and data acquisition procedure; abbreviation: PH_SR_ORTHO_DSM) •             Multispectral orthophotos and Digital Surface Models produced with the aid of a gyrocopter (PDF, Detailed description of sensors and data acquisition procedure; abbreviation: PANX_ORTHO_DSM) •             Classification results based on UAV- and a gyrocopter data (PDF, Detailed description of processing procedure for different classification levels; abbreviation: CLASSIF_PROD) •             German translated version of all above mentioned product portfolios (PDF, abbreviation: product_portfolio_collection_ger)

opencc-by-4.0Jan 2022View details →

mDRONES4rivers-project: Classification results based on UAV data of project sites situated in riparian zones along federal waterways in Germany with focus on the Rhine River, Germany

Spatially and temporally high-resolution data was acquired with the aid of multispectral sensors mounted on UAV and a gyrocopter platform for the purpose of classification. The work was part of the research and development project &bdquo;Modern sensors and airborne remote sensing for the mapping of vegetation and hydromorphology along Federal waterways in Germany“ (mDRONES4rivers) in cooperation of the German Federal Institute of Hydrology (BfG), Geocoptix GmbH, Hochschule Koblenz und JB Hyperspectral Devices.  Within the project period (2019-2022) an object oriented image classification was conducted based on UAV and gyrocopter data for different sites situated in Germany along the Rivers Rhine and Oder. All published data produced within the project can be found by searching for the keyword ‘mDRONES4rivers‘.  In this dataset, the following classification results and metadata of the project sites situated in riparian zones along federal waterways in Germany with focus on the Rhine River, Germany is available for download: •             Basic & Vegetation Classification (ESRI Shapefile; abbreviation: lvl2_vegetation_units) •             Classification of dominant stands (ESRI Shapefile; abbreviation: lvl4_dominant_stands ) •             Classification of substrat types (ESRI Shapefile; abbreviation: lvl4_substrate_types) •             associated reports (PDF; statistical and additional information on the classifiaction results and workflow) The above-mentioned files are provided for download as dataset stored in one directory per projekt site and season (e.g. mDRONES4rivers_Niederwerth_2019_03_Summer_Classification.zip = projectname_projectsite_year_no.season_name.season_product). To provide an overview of all files and general background information plus data preview the following files are additionally provided:  •             Portfolios (PDF, Detailed description of classification products and classification workflow, 1x for basic surface types, 1x for classification of vegetation units, 1x for classification of dominant stands,  1x for classification of substrate types) •            Color Coding table for the visualization of the classifiaction units (.xlsx)

opencc-by-4.0Feb 2022View details →

UAV test touch of 400 kV power-line

Test flight of a UAV with and without protective ESD shielding touching a 400 kV power-line.

opencc-by-4.0Mar 2022View details →

Dataset - Controlled release experiment to investigate uncertainties in UAV-based emission quantification for methane point sources

This dataset was created by Randulph Morales (randulph.morales@empa.ch) and was used for Morales et al. (2021) AMT publication (amt-2021-314).  A short description of the files is written in readme.txt The dataset contains: <ul> <li>QCLAS methane measurement</li> <li>Active AirCore methane measurement</li> <li>Meteorology files</li> </ul>

opencc-by-4.0Dec 2021View details →

Dataset of UAV thermal video sequences with annotations for MOTS benchmarking

Instance segmentation dataset created for the research 'Monitoring Mammalian Herbivores via Convolutional Neural Networks implemented on Thermal UAV imagery'. It comprises 959 frames, 20.647 masks, and 239 tracks, and consists of 7 video sequences depicting aerial thermal imagery of cattle collected with a UAV (Parrot ANAFI Thermal) in two outdoor farms in the Netherlands. Data were acquired at three temperatures (10ºC, 19ºC, and 26.5ºC), under sunny and overcast weather conditions, at various angles of inclination (including nadir), and at heights ranging between 8-28 meters. Ground truth was labeled manually with the Computer Vision Annotation Tool CVAT.

opencc-by-4.0Apr 2022View details →

Data and code for: Grain size of fluvial gravel bars from close-range UAV imagery – uncertainty in segmentation-based data

UAV images used for SfM model generation and all images (both SI and OM), in which we measured grain sizes. The code used for image processing and uncertainty estimation of grain size distributions as python files and executable jupyter notebooks, where the latter also serve as documentation.

opencc-by-4.0Apr 2022View details →

UAV outputs and associated field measurement of the herbaceous of a Sahelian Rangeland during the wet season in Northern Senegal

This dataset contains UAV outputs (mosaic and digital surface model) and field measurement of vegetation (shapefile) that were made in northern Senegal. Site gradient measurement The data was collected on a plot of the Centre of Zootechnical Researches of Dahra / ISRA during 2020 rainy season (from July 19, 2020, to September 17, 2020). The average rainfall for the period 1981-2018 was ranging from 221 mm.y-1 to 468 mm. y-1. The vegetation in the field is a herbaceous savannah where Vachellia tortilis and Balanites aegyptiaca are the dominant trees. Field measurement. UAV flight plan We used two different drones : Bluegrass and Anafi of Parrot. The Bluegrass of Parrot was used from 19/07/2020 to 04/08/2020. The Bluegrass flights were done at 60 meters of altitude, with a speed of 2 m s-1, and 90% of overlap rate between images, on a double grid of 100 m x 100 m. Anafi of Parrot was used for the rest of the season. The Anafi flights were done at 60 meters of altitude, with a speed of 2 m s-1, and 90% of overlap rate between images, on a double grid of 100 m x 100 m and the angle of inclination of the camera fixed at 80°. The flights have been done with PIX4D capture application at earlier in the day every two days. A total of 61 drone flights were conducted over the rainy season. Herbaceous Biomass Every two days , after drone flight, herbaceous measurements were carried out, in three plots of 1 m² distributed respectively under the crown of a tree, at the edge of the crown, and at a distance from the edge of the crown equal to the height of the tree. These plots were rotated among the trees in the field until all four azimuths of trees were covered.We collected Fresh mass and dry mass. Image analysis. The drone images taken for each day of collect, were analyzed in the software PIX4DMapper (Pix4D SA, Lausanne, Switzerland) by the Structure from Motion method. We used precisely the 3D mapping option of the software. Then for each flight we computed and exported an orthophotograph and a digital surface model. Data organization The data contains : <ul> <li>DSM that contains the surface model in tiff</li> <li>Mosaic that the orthomosaic in tiff.</li> <li>Data that contains the shapefile with the position and table with the field measurements</li> </ul>

UAV ESD Noise Recording with HEIST

Data recordings using HEIST while UAV is exposed to ESD. https://github.com/MaSkr09/heist_datalog.git

Magnetic Induced Injection on a UAV Recorded using HEIST

Test on for inducing 13.56 MHz EMI into a UAV. The noise is recorded using HEIST. https://github.com/MaSkr09/heist_datalog.git

UAV exposed to Ultra Bandwidth Noise Recorded using HEIST

Noise was recorded on an SBUS communication link on a UAV while exposed to UWB noise. HEIST is recording the data using an FPGA.   https://github.com/MaSkr09/heist_datalog.git

Burst Noise Injection through Antenna Recorded on a UAV at Logic Level using HEIST

A UAV exposed to burst noise injected through an antenna. The noise is recorded at logic level using HEIST.   https://github.com/MaSkr09/heist_datalog.git

opencc-by-4.0Jun 2022View details →

CoFly-WeedDB: A UAV image dataset for weed detection and species identification

The CoFly-WeedDB contains 201 RGB images (~436MB) from the attached camera of DJI Phantom Pro 4 from a cotton field in Larissa, Greece during the first stages of plant growth. The RGB images were collected while the Unmanned Aerial Vehicle (UAV) was performing a coverage mission over the field's area. During the designed mission, the camera angle was adjusted to -87°, vertically with the field. The flight altitude and speed of the UAV were equal to 5m and 3m/s, respectively, aiming to provide a close and clear view of the weed instances.  All images have been annotated by expert agronomists using the LabelMe annotation tool, providing the exact boundaries of 3 types of common weeds in this type of crop, namely (i) Johnson grass, (ii) Field bindweed, and (iii) Purslane. The dataset can be used alone and in combination with other datasets to develop AI-based methodologies for automatic weed segmentation and classification purposes.

opencc-by-4.0Feb 2022View details →

Replication Package of the study "Automated Identification and Qualitative Characterization of Safety Concerns Reported in UAV Software Platforms"

Description of the Dataset of the work "Automated Identification and Qualitative Characterization of Safety Concerns Reported in UAV Software Platforms" "1_Safety-Dataset" folder: This folder contains the bugs data and row data of all analyzed projects.  Specifically, this folder contains the following relevant entries        - "bugs" folder: It contains the bugs of all analyzed projects (PX4-merged.json.gz, dDronin-merged.json.gz, ardupilot-merged.json.gz)                             of all sentences extracted from the project issues      - "Dataset-safety-bugs.csv": For all projects, it contains the raw data of the set of sentences classified as safety and non-safety related.      "2_Scripts-and-generated-data (RQ1)" folder: This folder contains the scripts and code used to preprocess and analyze the issue data in                                               the context of RQ1  Specifically, this folder contains the following relevant entries         - "main-program.py" file: Main program executing all subscripts generating the data required for RQ1 (detailed in the following line)      - "utilities.R" file: (Utility) R script containing relevant functions for pre-processing/indexing text and issue data      - "1_Script-to-create-test-dataset.r" file:  R script containing simple code for analyzing issue data      - "2_MainScript.r" file: Main R program orchestrating the scripts "utilities.R" and "1_Script-to-create-test-dataset.r" execution      - "files-setDirectory" folder: Folder where data are generated and stored from the "main-program.py"      - "fasttext" folder: Folder where data used as input from fastText (by "main-program.py") are reported      - "cross-project-analysis" folder: Folder with data used for the cross-project analysis      - "main-program-grid-search.py" file: Main program executing all experiments for the grid search analysis "3_Results" folder: This folder contains the results, scripts and figures used to discuss results of the study.  Specifically, this folder contains the following relevant entries        - "RQ1" folder: This folder contains the results, scripts and figures used to discuss results of RQ1.      - "RQ2" folder: This folder contains the results, scripts and Tables used to discuss results of RQ2.

dryad40/100

Using Unoccupied Aerial Vehicles (UAVs) to map and monitor changes in emergent kelp canopy after an ecological regime shift

Kelp forests are complex underwater habitats that form the foundation of many nearshore marine environments and provide valuable services for coastal communities. Despite their ecological and economic importance, increasingly severe stressors have resulted in declines in kelp abundance in many regions over the past few decades, including the North Coast of California, USA. Given the significant and sustained loss of kelp in this region, management intervention is likely a necessary tool to reset the ecosystem and geospatial data on kelp dynamics are needed to strategically implement restoration projects. Because canopy-forming kelp forests are distinguishable in aerial imagery, remote sensing is an important tool for documenting changes in canopy area and abundance to meet these data needs. We used small unoccupied aerial vehicles (UAVs) to survey emergent kelp canopy in priority sites along the North Coast in 2019 and 2020 to fill a key data gap for kelp restoration practitioners working at local scales. With over 4,300 hectares surveyed between 2019 and 2020, these surveys represent the two largest marine resource-focused UAV surveys conducted in California to our knowledge. We present remote sensing methods using UAVs and a repeatable workflow for conducting consistent surveys, creating orthomosaics, georeferencing data, classifying emergent kelp, and creating kelp canopy maps that can be used to assess trends in kelp canopy dynamics over space and time. We illustrate the impacts of spatial resolution on emergent kelp canopy classification between different sensors to help practitioners decide which data stream to select when asking restoration and management questions at varying spatial scales. Our results suggest that high spatial resolution data of emergent kelp canopy from UAVs have the potential to advance strategic kelp restoration and adaptive management.

opencc-zeroSep 2022View details →

opencc-by-4.0Sep 2022View details →

Spekboom UAV imagery and reference data

Dataset and products for the publication Automated mapping of Portulacaria afra canopies for restoration monitoring with convolutional neural networks and heterogeneous unmanned aerial vehicle imagery.

opencc-by-4.0Aug 2022View details →

UAV observations of the NDVI, snow depth and melt out date, retreived ar the Izas Experimental Catchment in 2020 and 2021

This dataset includes very high spatial resolution observations at 1 m spatial resolution observations of the snow depth, the NDVI and the melt-out date (DOY of year) acquired with an Unmanned Aerial Vehicle at a sub-alpine site in the Pyrenees, the Izas Experimental Catchment. During two snow seasons (2019-2020 and 2020-2021), 14 NDVI and 17 snow depth distributions were acquired over 48ha. From the snow depth observations the melt-out dates have been derived. Also information on the main topographic variables (elevation, aspect and slope) is included, with same spatial resolution, in this dataset.

Figure 9. Trajectory Algorithm Simulation-Design and Implementation of a Fully Autonomous UAV's Navigator Based on Omni-directional Vision System

We have presented the system for a fully autonomous navigation of an UAV based on Omni directional vision system and image processing. we explain vision system configuration ,image processing and feature extraction methods and finaly suggest an algorithm based on potential field for navigation of an UAV.

Figure 8. Potential at every point; it is highest in the obstacles and lowest at the goal-Design and Implementation of a Fully Autonomous UAV's Navigator Based on Omni-directional Vision System

The numerical potential field path planner is guaranteed to produce a path even if the start or goal is placed in an obstacle. If there is no possible way to get from the start to the goal without passing through an obstacle then the path planner will generate a path through the obstacle, although if there is any alternative then the path will do that instead. For this reason, it is important to make sure that there is some possible path, although there are ways around this restriction such as returning an error if the potential at the start point is too high. The path is found by moving to the neighboring square with the lowest potential, starting at any point in the space and stopping when the goal is reached.

Figure 7. Obstacle force (repulsive potential) and goal force obstacle force-Design and Implementation of a Fully Autonomous UAV's Navigator Based on Omni-directional Vision System

Figure 6. Goal force-Design and Implementation of a Fully Autonomous UAV's Navigator Based on Omni-directional Vision System

Since the motion trajectory of UAV is divided into several median points that the UAV should reach them one by one in a sequence the output obtained after the execution of AI will be a set of position and velocity vectors. So the task of the trajectory will be to guide the UAV through the obstacles to reach the destination. The routine used for this purpose is the potential field method (also an alternative new method is in progress which models the UAV motion through opponents same as the owing of a bulk of water through obstacles) [5]. In this method, different electrical charges are assigned to UAV, obstacles, and the destination. Then by calculating the potential field of this system of charges a path will be suggested for the UAV. At a higher level, predictions can be used to anticipate the position of the obstacles and make better decisions in order to reach the desired vector. In our path- planning algorithm, an articial potential field is set up in the space; that is, each point in the space is assigned a scalar value. The value at the goal point is set to be 0 and the value of the potential at all other points is positive.