Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
59
datasets available to search
ShareScore release 0.9.0
Dataset results
59 results for “Multi-sensor”
Multi-sensor mapping and localization datasets
<p>This is a dataset for testing outdoors mapping and localization algorithms. It contains two Rosbag files that provide different measurements from an 3D Velodyne LIDAR, a visual sensor, an altimeter, an IMU, and Ultra-Wide-Band Time-of-Flight sensors, all mounted in an aerial vehicle. The ground-truth localization of the robot is given by a RTK GPS with accuracy of < 2cm. The transformations between sensor frames are also given in the bags. The flight experiments were conducted in an outdoors scenario near Seville, during September 2018.</p>
Mapping Soil Organic Carbon in the World's Largest Arid Mangrove Forest (Indus Delta, Pakistan): A Multi-Sensor Remote Sensing and Machine Learning Approach
<p>Mangrove forests play a crucial role in carbon sequestration, especially in arid regions where their ability to store carbon in soil is vital for mitigating climate change. The Indus Delta in Pakistan, the world’s largest arid mangrove forest system, lacks spatially explicit data on Soil Organic Carbon (SOC) despite its importance for conservation and carbon budgeting. This study aims to establish a baseline SOC map 2020 at 10 m spatial resolution using Sentinel-1 (Synthetic Aperture Radar) and Sentinel-2 (MultiSpectral Instrument) satellite imagery, integrated with in-situ soil sampling. SOC predictions were made using a Classification and Regression Tree (CART) machine learning model within the Google Earth Engine platform, leveraging 40 predictor variables, including spectral bands and derived indices. A total of 53 topsoil (0-10 cm) samples were collected in February 2020 across the Indus Delta, and SOC was analyzed using the Walkley-Black method. The results showed an average SOC value of 65.88 Mg C ha⁻¹ with substantial spatial variability, ranging from 15.06 Mg C ha⁻¹ to 138.03 Mg C ha⁻¹ with a total of 0.91 Pg C. The CART model demonstrated high accuracy, with an R² of 0.95 and an RMSE of 9.18 Mg C ha⁻¹. However, the region faces challenges such as seawater intrusion and salinity, which threaten its ability to sequester carbon. With the first high-resolution SOC map for the Indus Delta, this study provides valuable insights for ecosystem management, conservation planning, and carbon budgeting. These findings of this study have the potential to significantly influence initiatives like REDD+ and Blue Carbon projects, which aim to enhance carbon sequestration while addressing the ecological challenges facing Pakistan’s mangroves</p>
Transition and Drivers of Elastic to Inelastic Deformation in the Abarkuh Plain from InSAR Multi-Sensor Time Series and Hydrogeological Data
<p>This repository contains the datasets used in <a href="https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2023JB026430">Mirzadeh et al., 2023</a>. It includes three InSAR time-series datasets from the Envisat descending orbit, ALOS-1 ascending orbit, and Sentinel-1A in ascending and descending orbits, acquired over the Abarkuh Plain, Iran, as well as the geological map of the study area and the GNSS and hydrogeological data used in this research.</p> <p>Dataset 1: Envisat descending track 292</p> <ul> <li>Date: 06 Oct 2003 - 05 Sep 2005 (12 acquisitions)</li> <li>Processor: ISCE/stripmapStack + MintPy</li> <li>Displacement time-series (in HDF-EOS5 format): timeseries_LOD_tropHgt_ramp_demErr.h5</li> <li>Mean LOS Velocity (in HDF-EOS5 format): velocity.h5</li> <li>Mask Temporal Coherence (in HDF-EOS5 format): maskTempCoh.h5</li> <li>Geometry (in HDF-EOS5 format): geometryRadar.h5</li> </ul> <p>Dataset 2: ALOS-1 ascending track 569</p> <ul> <li>Date: 06 Dec 2006 - 17 Dec 2010 (14 acquisitions)</li> <li>Processor: ISCE/stripmapStack + MintPy</li> <li>Displacement time-series (in HDF-EOS5 format): timeseries_ERA5_ramp_demErr.h5</li> <li>Mean LOS Velocity (in HDF-EOS5 format): velocity.h5</li> <li>Mask Temporal Coherence (in HDF-EOS5 format): maskTempCoh.h5</li> <li>Geometry (in HDF-EOS5 format): geometryRadar.h5</li> </ul> <p>Dataset 2: Sentinel-1 ascending track 130 and descending track 137</p> <ul> <li>Date: 14 Oct 2014 - 28 Mar 2020 (129 ascending acquisitions) + 27 Oct 2014 - 29 Mar 2020 (114 descending acquisitions)</li> <li>Processor: ISCE/topsStack + MintPy</li> <li>Displacement time-series (in HDF-EOS5 format): timeseries_ERA5_ramp_demErr.h5</li> <li>Mean LOS Velocity (in HDF-EOS5 format): velocity.h5</li> <li>Mask Temporal Coherence (in HDF-EOS5 format): maskTempCoh.h5</li> <li>Geometry (in HDF-EOS5 format): geometryRadar.h5</li> </ul> <p>The time series and Mean LOS Velocity (MVL) products can be georeferenced and resampled using the makTempCoh and geometryRadar products and the MintPy commands/functions.</p>
A multi-sensor gait dataset collected under non-standardized dual-task conditions
Open the record for dataset details and reuse information.
Ljubljana Multi-Sensor Indoor and Outdoor PM Exposure, Environment, and Personal Health Dataset
<p>This dataset was compiled between February 16, 2019, and May 25, 2019, involving 82 participants residing in the municipality of Ljubljana. Data collected before March 12th represents the "heating season," while data after April 27th corresponds to the "non-heating season." This dataset is the cleaned/filtered version with outliers caused by software or hardware errors removed.</p><p>Derived from the larger ICARUS project in Ljubljana, this dataset integrates various data sources, including:</p><ul><li>Participant Questionnaires: Containing certain individual information, i.e., age, height, gender.</li><li>Time Activity Diaries: Providing hourly activity records for each participant.</li><li>Personal PM Monitors: Measuring indoor and outdoor PM concentrations.</li><li>Smart Activity Trackers: Recording heart rate and movement data.</li><li>Indoor Air Quality Station: Capturing indoor air quality parameters.</li></ul><p>The dataset includes the calculation of inhalation rate based on heart rate data, allowing for the determination of inhalation rate-adjusted exposure or intake dose.</p><p>This version of the dataset is in .csv format.</p>
Datasets associated with paper "Five decades of Abramov glacier dynamics reconstructed with multi-sensor optical remote sensing", by Enrico Mattea et al.
<p>This archive contains Digital Elevation Models and orthoimages produced within the study "Five decades of Abramov glacier dynamics reconstructed with multi-sensor optical remote sensing", published on The Cryosphere by Enrico Mattea et al.</p> <p>Assets include derivative products of SPOT satellite scenes, acquired by CNES’s Spot World Heritage Programme, and of Pléiades <span><span><strong>©</strong></span></span>CNES 2015, 2020, 2022, Distribution AIRBUS DS.</p>
Multi-Sensor Dataset in outdoor and indoor environment from Android Smart Devices and ULISS
<p>This dataset contains data acquired on various Android smart devices, i.e., smartphone and smartwatches (Mimir, TAU) and ULISS devices (AME-GEOLOC). The surveys have been performed in multiple environment (open-sky, urban canyon, light indoor, deep indoor), in different carrying mode (texting, swinging, pocket). The raw sensor data logged are : GNSS raw measurements and position fix, accelerometer, gyroscope, magnetometer, barometer, step counter/detector. The dataset is provided under the CC-BY 4.0 license. More information are provided inside the ''notes.txt' provided along the dataset, as well as in our related publication.</p>
IMAD-DS: A Dataset for Industrial Multi-Sensor Anomaly Detection Under Domain Shift Conditions
<p>IMAD-DS is a dataset developed for multi-rate multi-sensor anomaly detection (AD) in industrial environments, that considers varying operational and environmental conditions known as domain shifts.</p> <p><strong>Dataset Overview:</strong></p> <p>This dataset includes data from two scaled industrial machines: a robotic arm and a brushless motor.</p> <p>It includes both normal and abnormal data recorded under various operating conditions to account for domain shifts. These shifts are categorized into:</p> <p>Robotic Arm: The robotic arm is a scaled version of a robotic arm used to move silicon wafers in a factory. Anomalies are created by removing bolts at the nodes of the arm, resulting in an imbalance in the machine.<br>Brushless Motor: The brushless motor is a scaled representation of an industrial brushless motor. Two anomalies are introduced: first, a magnet is moved closer to the motor load, causing oscillations by interacting with two symmetrical magnets on the load; second, a belt that rotates in unison with the motor shaft is tightened, creating mechanical stress.</p> <p>The following domain shifts are included in the dataset:</p> <p>Operational Domain Shifts: Variations caused by changes in machine conditions (e.g., load changes for the robotic arm and speed changes for the brushless motor).</p> <p>Environmental Domain Shifts: Variations due to changes in background noise levels.</p> <p>Combinations of operating and environmental conditions divide each machine's dataset into two subsets: the <em>source domain</em> and the <em>target domain</em>. The source domain has a large number of training examples. The target domain, instead, has limited training data. This discrepancy highlights a common issue in the industry where sufficient training data is often unavailable for the target domain, as machine data is collected under controlled environments that do not fully represent the deployment environments.</p> <p> </p> <p><strong>Data Collection and Processing:</strong></p> <p>Data is collected using the STEVAL-STWINBX1 IoT Sensor Industrial Node. The sensor used to record the dataset are the following.</p> <p>· Analog Microphone (16 kHz)</p> <p>· 3-axis Accelerometer (6.7 kHz)</p> <p>· 3-axis Gyroscope (6.7 kHz)</p> <p>Recordings are conducted in an anechoic chamber to control acoustic conditions precisely</p> <p><strong>Data Format:</strong><strong><br></strong>Files are already divided into train and test sets. Inside each folder, each sensor's data is stored in a separate '.parquet' file.</p> <p>Sensor files related to the <em>same</em> segment of machine data share a unique ID. The mapping of each machine data segment to the sensor files is given in .csv files inside the train and test folders. Those .csv files also contain metadata denoting the operational and environmental conditions of a specific segment.</p> <p> </p> <p> </p> <p> </p>
The Multi-Sensor Distance Accuracy Study
ClinicalTrials.gov study NCT02241993. IPD Sharing: Not stated. Countries: 1. Publications: 3.
Data from: Give the machine a hand: a Boolean time-based decision-tree template for rapidly finding animal behaviours in multi-sensor data
1. The development of multi-sensor animal-attached tags, recording data at high frequencies, has enormous potential in allowing us to define animal behaviour. 2. The high volumes of data, are pushing us towards machine-learning as a powerful option for distilling out behaviours. However, with increasing parallel lines of data, systems become more likely to become processor limited and thereby take appreciable amounts of time to resolve behaviours. 3. We suggest a Boolean approach whereby critical changes in recorded parameters are used as sequential templates with defined flexibility (in both time and degree) to determine individual behavioural elements within a behavioural sequence that, together, makes up a single, defined behaviour. 4. We tested this approach, and compared it to a suite of other behavioural identification methods, on a number of behaviours from tag-equipped animals; sheep grazing, penguins walking, cheetah stalking prey and condors thermalling. 5. Overall behaviour recognition using our new approach was better than most other methods due to; (i) its ability to deal with behavioural variation and (ii) the speed with which the task was completed because extraneous data are avoided in the process. 6. We suggest that this approach is a promising way forward in an increasingly data-rich environment and that workers sharing algorithms can provide a powerful library for the benefit of all involved in such work.
Spectral-temporal features over South Africa (2013-2015) derived from multi-sensor Landsat imagery
<p>The three data sets are spectral-temporal features derived from multi-sensor Landsat imagery over South Africa. They were derived as follows:</p> <p>All Landsat-5, -7 and -8 data from 2013 to 2015 covering South Africa (70 tiles) were acquired and pre-processed following the procedure implemented in Hansen et al. (2013), Potapov et al. (2014), Potapov et al. 2012. Note that four tiles (path/row: 176/77, 175/78, 174/78, 174/79) were discarded because no crop is grown there. Four spectral bands were kept: the red, the near-infrared (NIR), and the two short-wave infrared (SWIR) bands. The blue and green bands were discarded due to their sensitivity to atmospheric effects. We applied a three-step procedure to normalize the radiometry. First, Landsat data were converted to top-of-atmosphere reflectance and then normalized by taking the corresponding MODIS top-of-canopy reflectance data as target. Third, we adjusted cross-track surface anisotropy effects by modeling the Landsat reflectance per spectral band as a function of the viewing angle. The above-mentioned processing steps incrementally improved the appearance of the data, providing more spatial coherence and increasing the generalization and internal consistency of the multi-spectral feature space.</p> <p> </p> <p>Hansen MC, Potapov PV, Moore R, Hancher M, Turubanova S, Tyukavina A, et al. High-resolution global maps of 21st-century forest cover change. science. 2013;342(6160):850{853.</p> <p><br> Potapov P, Dempewolf J, Talero Y, Hansen M, Stehman S, Vargas C, et al. National satellite-based humid tropical forest change assessment in Peru in support of REDD+ implementation. Environmental Research Letters. 2014;9(12):124012.</p> <p><br> Potapov PV, Turubanova S, Tyukavina A, Krylov A, McCarty J, Radeloff V, et al. Eastern Europe's forest cover dynamics from 1985 to 2012 quantified from the full Landsat archive. Remote Sensing of Environment. 2015;159:28 43.</p>
ROV-Based Multi-Sensor Dataset: Synchronized Camera and Sonar images taken in the Tropical Waters of the Red Sea, Eilat
<p><strong>Description:</strong></p> <p>This dataset consists of approximately 46,928 synchronized image pairs collected by the Blue-ROV2. The images were captured using a machine-vision camera (IDS UI-3260CP-C-HQ) and a BluePrint Oculus M1200d Forward-Looking Sonar (FLS). Both sensors were installed with the FLS tilted 15 degrees downward to achieve optimal coverage of the terrain and optimal FOV overlap.</p> <p>The data was collected to train and evaluate a comprehensive perception and obstacle avoidance framework.</p> <p> </p> <p><strong>Context:</strong></p> <p>This dataset is the second installment in our collection of synchronized multi-sensor underwater datasets, aimed at enabling advanced research in multi-modal sensor fusion, obstacle detection, and navigation for autonomous underwater vehicles (AUVs). The data was collected using the Blue-ROV2 Remotely Operated Vehicle (ROV) in the tropical waters of the Red Sea, off the coast of Eilat, Israel. This data captures diverse underwater environments and is part of a research project focused on developing fusion models for improved obstacle detection and navigation in AUVs.</p> <p> </p> <p><strong>Content:</strong></p> <p>The data encompasses several sites within the tropical waters of the Red Sea, Eilat, including corals, rocks, shipwrecks, man-made structures, piers, and caves. The ROV platform was operated by divers, ensuring accurate positioning and coverage. Data was acquired at depths ranging from 3 to 12 meters at different times from dawn to dusk.</p> <p><strong> </strong></p> <p><strong>Dataset Composition:</strong><strong><br></strong></p> <div> <table> <tbody> <tr> <td> <p>Site</p> </td> <td> <p>Recording Session</p> </td> <td> <p>Image Pairs</p> </td> <td> <p>Description</p> </td> </tr> <tr> <td> <p>Tropical Site 1</p> </td> <td> <p>20221211_092506</p> <p>20221211_133252</p> </td> <td> <p>10,915</p> <p>7,978</p> </td> <td> <p>Pier, rocks, corals</p> </td> </tr> <tr> <td> <p>Tropical Site 2</p> </td> <td> <p>20221212_095821</p> <p>20221212_141308</p> </td> <td> <p>9,900</p> <p>8,475</p> </td> <td> <p>Man-made structure, </p> <p>rocks, corals</p> </td> </tr> <tr> <td> <p>Tropical Site 3</p> </td> <td> <p>20221213_102542</p> </td> <td> <p>9,390</p> </td> <td> <p>Rocks, corals</p> </td> </tr> <tr> <td> <p>Total</p> </td> <td> </td> <td> <p>46,928 </p> </td> <td> </td> </tr> </tbody> </table> </div> <p><strong> </strong></p> <p>The dataset is organized into separate sessions, each representing a specific dive or experiment. Within each session, data is further categorized into modalities: camera (FLC images), sonar (FLS images), and depth. Each modality directory contains the corresponding data files in PNG format for images and CSV format for depth data.</p> <p><strong> </strong></p> <p>Each modality directory includes:</p> <ul> <li> <p>A `camera.csv` file for the camera modality that maps each image file to its respective timestamp.</p> </li> <li> <p>A `sonar.csv` file for the sonar modality that maps each image file to its respective timestamp.</p> </li> <li> <p>The depth data in `depth.csv` formatted with `timestamp` and `value`.</p> </li> </ul> <p>Additionally, a `samples.json` file documents the relationship between uni-modal and multi-modal samples, enabling easy association of data from different modalities.</p> <p><strong> </strong></p> <p><strong>Technical Details:</strong></p> <ul> <li> <p>Camera: IDS UI-3260CP-C-HQ</p> </li> <ul> <li> <p>Image dimensions: 1936x1216 pixels (downscaled to 968 × 608 for this dataset)</p> </li> <li> <p>Sensor type: Sony IMX249 1/1.2" CMOS</p> </li> <li> <p>Lens: Tamron M112FM06</p> </li> <li> <p>Captured bit depth: 8-bit</p> </li> <li> <p>Frame rate: 5 Hz</p> </li> </ul> <li> <p>Sonar: BluePrint Oculus M1200d</p> </li> <ul> <li> <p>Operating frequency: 1.2 MHz (low frequency mode)</p> </li> <li> <p>Maximum range: 40 m (set to 15 m for this dataset)</p> </li> <li> <p>Horizontal aperture: 130°</p> </li> <li> <p>Vertical aperture: 20°</p> </li> <li> <p>Number of beams: 512</p> </li> <li> <p>Angular resolution: 0.6°</p> </li> <li> <p>Beam separation: 0.25°</p> </li> <li> <p>Image resolution: 544x300 pixels</p> </li> <li> <p>Coordinate system: Polar</p> </li> <li> <p>Frame rate: 5 Hz</p> </li> </ul> <li> <p>Depth: Blue-Robotics Ping2 Sonar Altimeter and Echosounder</p> </li> <ul> <li> <p>Frequency: 115 kHz</p> </li> <li> <p>Source Level: 198 dB re 1µPa @ 1m</p> </li> <li> <p>Beamwidth: 25 degrees</p> </li> <li> <p>Typical Minimum Range: 0.3 m (1 ft)</p> </li> <li> <p>Typical Usable Range: 100 m (328 ft)</p> </li> <li> <p>Range Resolution: 0.5% of range</p> </li> <li> <p>Depth Rating: 300 m (984 ft)</p> </li> <li> <p>Data format: CSV</p> </li> <li> <p>Columns:</p> </li> <ul> <li> <p>timestamp: Unix timestamp (seconds)</p> </li> <li> <p>value: Depth value (meters)</p> </li> </ul> <li> <p>Sample rate: 5 Hz</p> </li> </ul> </ul> <p><strong> </strong></p> <p><strong>Example File Tree Layout:</strong></p> <p>```<br>${session}/<br>${dataset}/<br>camera/<br>camera.csv<br>00000001.png<br>00000002.png<br>…<br>sonar/<br>sonar.csv<br>00000001.png<br>00000002.png<br>…<br>depth/<br>depth.csv<br>samples.json<br>```<strong> <br><br>Example File Content:</strong></p> <p><strong> </strong>camera.csv<br>```<br>timestamp,filename<br>1644234340.181234,00000001.png<br>1644234343.375667,00000002.png<br>```</p> <p><strong> </strong>sonar.csv<br>```<br>timestamp,filename<br>1644234340.181234,00000001.png<br>1644234343.375667,00000002.png<br>```</p> <p><strong> </strong>depth.csv<br>```<br>timestamp,value<br>1644234340.181234,5.4<br>1644234343.375667,6.1<br>```</p> <p><strong> </strong>samples.json</p> <p>```<br>{<br> "samples": [<br> {<br> "camera": [<br> 0<br> ],<br> "depth": [<br> 0<br> ],<br> "sonar": [<br> 0<br> ]<br> },<br> {<br> "camera": [<br> 1<br> ],<br> "depth": [<br> 1<br> ],<br> "sonar": [<br> 1<br> ]<br> }<br>]</p> <p>```</p> <p>By providing synchronized and aligned camera, sonar imagery, and depth data, this dataset enables researchers to explore novel algorithms and techniques for multi-modal sensor fusion in the context of autonomous underwater vehicles operating in the tropical waters of the Red Sea.</p> <p><strong>Acknowledgements</strong></p> <p>The data in this repository is part of the DeeperSense project that received funding from the European Commission, Program H2020-ICT-2020-2 ICT-47-2020, Project Number: 101016958.</p>
Data from: Give the machine a hand: a Boolean time-based decision-tree template for rapidly finding animal behaviours in multi-sensor data
Open the record for dataset details and reuse information.
Saildrone 2021 Arctic field campaign for the Multi-Sensor Improved SST (MISST) project
The Saildrone Arctic 2021 dataset presents a unique collection of high-quality, near real-time, multivariate surface ocean, and atmospheric observations obtained through the deployment of Saildrone, an innovative wind and solar-powered uncrewed surface vehicle (USV). Saildrone is capable of extended missions lasting up to 12 months, covering vast distances at typical speeds of 3-5 knots and operates autonomously, relying solely on wind propulsion, while its navigation can be remotely guided from land. The 2021 Saildrone Arctic campaign featured two Saildrone USVs deployed during a 76-day cruise in the Bering and Chukchi Seas, spanning from 6 July 2021 to 20 September 2021. The primary mission objective for 2021 was to gather comprehensive atmospheric and oceanographic data in Alaskan arctic waters, with special emphasis on better understanding the spatial/temporal scales of air-sea covariance in the Chukchi Sea, which was accomplished by running a series of parallel tracks using the two Saildrones at varying horizontal offsets. Please see the cruise report: https://archive.podaac.earthdata.nasa.gov/podaac-ops-cumulus-docs/insitu/open/L2/saildrone/docs/2021_Saildrone_Arctic_Cruise_Report.pdf <p>During the Arctic campaign, Saildrones SD-1057 and SD-1058 ran transects in the Chukchi Sea, approaching the sea ice edge (up to 50 km away) to measure air-sea heat and momentum fluxes in the ocean near sea ice and to validate satellite sea-surface temperature measurements in the Arctic. Each Saildrone was equipped with a suite of instruments to measure various parameters, including air temperature, relative humidity, barometric pressure, surface skin temperature, wind speed and direction, wave height and period, seawater temperature and salinity, chlorophyll fluorescence, and dissolved oxygen. Additionally, both vehicles utilized 300 kHz acoustic Doppler current profilers (ADCP) to measure near-surface currents.\The Saildrone Arctic 2021 dataset, part of the Multi-sensor Improved Sea-Surface Temperature (MISST) project, encompasses two netCDF format files for each deployed Saildrone. The first file integrates saildrone platform telemetry and surface observational data at 1-minute temporal resolution including key parameters such as air temperature, sea surface skin, and bulk temperatures, salinity, oxygen and chlorophyll-a concentrations, barometric pressure, and wind speed and direction. The second file focuses on ADCP current vector data, providing depth-resolved information to 100m at 2m intervals and binned temporally at 5-minute resolution. This project, funded by NASA through the National Ocean Partnership Program (NOPP), demonstrates a commitment to advancing scientific understanding of the Arctic environment through innovative and autonomous observational technologies.<p>The Saildrone Arctic 2021 dataset, part of the Multi-sensor Improved Sea-Surface Temperature (MISST) project, encompasses two netCDF format files for each deployed Saildrone. The first file integrates saildrone platform telemetry and surface observational data at 1-minute temporal resolution including key parameters such as air temperature, sea surface skin, and bulk temperatures, salinity, oxygen and chlorophyll-a concentrations, barometric pressure, and wind speed and direction. The second file focuses on ADCP current vector data, providing depth-resolved information to 100m at 2m intervals and binned temporally at 5-minute resolution. This project, funded by NASA through the National Ocean Partnership Program (NOPP), demonstrates a commitment to advancing scientific understanding of the Arctic environment through innovative and autonomous observational technologies.
GPM Ground Validation National Mosaic and Multi-Sensor QPE (NMQ) System IFloodS
The GPM Ground Validation National Mosaic and Multi-Sensor QPE (NMQ) System IFloodS dataset contains quality control products, real time rain rate estimates, hourly precipitation rate estimates, and three-dimensional reflectivity products. These data products are also referred to as Multi-Radar Multi-Sensor Precipitation Reanalysis for Satellite Validation (MRMS) product and were created using the NOAA NMQ System which ingests Weather Surveillance Radar 88 Doppler (WSR-88D) radar data, Rapid Update Cycle (RUC) model analysis fields, and Hydrometeorological Automated Data Systems (HADS) gauge data. The files provided in this dataset are from the NMQ system output obtained during the GPM Iowa Flood Studies (IFloodS) field campaign that occurred throughout Iowa. These data are available in ASCII, netCDF-4, and binary formats for the dates between April 1, 2013 through June 30, 2013.
MUSERC: Multi-Sensor Cello Recordings for Instantaneous Frequency Estimation
<p>Estimating the fundamental frequency (F0) of a signal is a well studied task in audio signal processing with many applications. If the F0 varies over time, the complexity increases, and it is also more difficult to provide ground truth data for evaluation. In this project we present a dataset of cello recordings addressing the lack of reference annotations for musical instruments. Besides audio data, we include sensor recordings capturing the finger position on the fingerboard which is converted into an instantaneous frequency estimate. This is similar to speech processing, where the electroglottograph (EGG) is able to capture the excitation signal of the vocal tract, which is then used to generate a reference instantaneous F0. Inspired by this approach, we included high speed video camera recordings to extract the excitation signal originating from the moving string. The derived data can be used to analyze vibratos — a very commonly used playing style</p>
MuSHRoom: Multi-Sensor Hybrid Room Dataset for Joint 3D Reconstruction and Novel View Synthesis (Kinect Part 1)
<p>Metaverse technologies demand accurate, real-time, and immersive modeling on consumer-grade hardware for both non-human perception (e.g., drone/robot/autonomous car navigation) and immersive technologies like AR/VR, requiring both structural accuracy and photorealism. However, there exists a knowledge gap in how to apply geometric reconstruction and photorealism modeling (novel view synthesis) in a unified framework.</p><p>To address this gap and promote the development of robust and immersive modeling and rendering with consumer-grade devices, first, we propose a real-world Multi-Sensor Hybrid Room Dataset (MuSHRoom). Our dataset presents exciting challenges and requires state-of-the-art methods to be cost-effective, robust to noisy data and devices, and can jointly learn 3D reconstruction and novel view synthesis, instead of treating them as separate tasks, making them ideal for real-world applications. Second, we benchmark several famous pipelines on our dataset for joint 3D mesh reconstruction and novel view synthesis. Finally, in order to further improve the overall performance, we propose a new method that achieves a good trade-off between the two tasks. Our dataset and benchmark show great potential in promoting the improvements for fusing 3D reconstruction and high-quality rendering in a robust and computationally efficient end-to-end fashion.</p>
MuSHRoom: Multi-Sensor Hybrid Room Dataset for Joint 3D Reconstruction and Novel View Synthesis (Kinect Part 2)
<p>Metaverse technologies demand accurate, real-time, and immersive modeling on consumer-grade hardware for both non-human perception (e.g., drone/robot/autonomous car navigation) and immersive technologies like AR/VR, requiring both structural accuracy and photorealism. However, there exists a knowledge gap in how to apply geometric reconstruction and photorealism modeling (novel view synthesis) in a unified framework.</p><p>To address this gap and promote the development of robust and immersive modeling and rendering with consumer-grade devices, first, we propose a real-world Multi-Sensor Hybrid Room Dataset (MuSHRoom). Our dataset presents exciting challenges and requires state-of-the-art methods to be cost-effective, robust to noisy data and devices, and can jointly learn 3D reconstruction and novel view synthesis, instead of treating them as separate tasks, making them ideal for real-world applications. Second, we benchmark several famous pipelines on our dataset for joint 3D mesh reconstruction and novel view synthesis. Finally, in order to further improve the overall performance, we propose a new method that achieves a good trade-off between the two tasks. Our dataset and benchmark show great potential in promoting the improvements for fusing 3D reconstruction and high-quality rendering in a robust and computationally efficient end-to-end fashion.</p>
MuSHRoom: Multi-Sensor Hybrid Room Dataset for Joint 3D Reconstruction and Novel View Synthesis (Kinect Part 3)
<p>Metaverse technologies demand accurate, real-time, and immersive modeling on consumer-grade hardware for both non-human perception (e.g., drone/robot/autonomous car navigation) and immersive technologies like AR/VR, requiring both structural accuracy and photorealism. However, there exists a knowledge gap in how to apply geometric reconstruction and photorealism modeling (novel view synthesis) in a unified framework.</p><p>To address this gap and promote the development of robust and immersive modeling and rendering with consumer-grade devices, first, we propose a real-world Multi-Sensor Hybrid Room Dataset (MuSHRoom). Our dataset presents exciting challenges and requires state-of-the-art methods to be cost-effective, robust to noisy data and devices, and can jointly learn 3D reconstruction and novel view synthesis, instead of treating them as separate tasks, making them ideal for real-world applications. Second, we benchmark several famous pipelines on our dataset for joint 3D mesh reconstruction and novel view synthesis. Finally, in order to further improve the overall performance, we propose a new method that achieves a good trade-off between the two tasks. Our dataset and benchmark show great potential in promoting the improvements for fusing 3D reconstruction and high-quality rendering in a robust and computationally efficient end-to-end fashion.</p>
MuSHRoom: Multi-Sensor Hybrid Room Dataset for Joint 3D Reconstruction and Novel View Synthesis (Kinect Part 4)
<p>Metaverse technologies demand accurate, real-time, and immersive modeling on consumer-grade hardware for both non-human perception (e.g., drone/robot/autonomous car navigation) and immersive technologies like AR/VR, requiring both structural accuracy and photorealism. However, there exists a knowledge gap in how to apply geometric reconstruction and photorealism modeling (novel view synthesis) in a unified framework.</p><p>To address this gap and promote the development of robust and immersive modeling and rendering with consumer-grade devices, first, we propose a real-world Multi-Sensor Hybrid Room Dataset (MuSHRoom). Our dataset presents exciting challenges and requires state-of-the-art methods to be cost-effective, robust to noisy data and devices, and can jointly learn 3D reconstruction and novel view synthesis, instead of treating them as separate tasks, making them ideal for real-world applications. Second, we benchmark several famous pipelines on our dataset for joint 3D mesh reconstruction and novel view synthesis. Finally, in order to further improve the overall performance, we propose a new method that achieves a good trade-off between the two tasks. Our dataset and benchmark show great potential in promoting the improvements for fusing 3D reconstruction and high-quality rendering in a robust and computationally efficient end-to-end fashion.</p>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.