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.
1,308
datasets available to search
ShareScore release 0.9.0
Dataset results
1,308 results for “Vehicle”
Hybrid Vehicle Research Data
Open the record for dataset details and reuse information.
BadODD: Bangladeshi Autonomous Vehicle Object Detection Dataset
<p>The dataset covers the following 9 districts in Bangladesh: Sylhet, Dhaka, Rajshahi, Mymensingh, Maowa, Chittagong, Sirajganj, Sherpur, and Khulna. Participants will encounter a wide range of road types, including towns, expressways, highways, and village roads. This diversity in locations aims to challenge algorithms to perform well across various driving contexts commonly encountered on Bangladesh roads.</p> <p> </p>
SPARCS-WP3_Espoo_City_Total number of vehicles in local transportation
<p>Number of vehicles registered in the Espoo area.</p>
Supplementary Dataset for V8s: An Edge/Cloud Deployable Kubernetes Task Offloading Framework for Smart Vehicles
<p>The supplementary dataset related to the plots in the paper "V8s: An Edge/Cloud Deployable Kubernetes Task Offloading Framework for Smart Vehicles" is published on this page. You can download the zip file with the following contents:</p> <p> </p> <p>exec-time/<br>├── edge-face-detect.csv<br>├── edge-object-recognition.csv<br>├── nano-face-detect.csv<br>├── nano-gpu-object-recognition.csv<br>├── nano-object-recognition.csv<br>├── rahti-face-detect.csv<br>├── rahti-object-recognition.csv<br>├── rahti2-face-detect.csv<br>├── rahti2-object-recognition.csv<br>├── ras-face-detect.csv<br>└── ras-object-recognition.csv<br>latency/<br>├── 5g.csv (when accessing the edge server using 5GTN connectivity)<br>├── edge.csv (when accessing the edge server using WiFi and VPN)<br>└── rahti-cloud.csv (when accessing the Rahti using WiFi)</p> <p> </p> <p> </p> <p>There are two folders in the dataset, one is for the latency information when using 5G connection and WiFi connection when using the resources. The other folder is for the execution time of the two implemented applications --- object recognition and face detection --- using the V8s framework in various execution environments.</p> <p>The file size is about 209 MiB.</p>
Consumer Attitudes towards Electric Vehicles in Jabodetabek
Open the record for dataset details and reuse information.
Autonomous Vehicles_VSIM Simulator_Dataset
<p>The VSIM dataset is a specially designed collection of 5,000 images, created to enhance object detection in autonomous vehicle (AV) applications. Developed with the VSIM simulator in Unity, this dataset captures eight distinct categories across realistic driving scenarios, with a focus on representing varied environments and conditions for AVs. To ensure high-quality data, images were preprocessed and augmented using Roboflow. The dataset is divided into training, validation, and testing sets, with a unique setup for federated learning, where training data is split across three clients. Each client is configured to detect four key object classes—humans, cars, road signs, and bikes—supporting research in both centralized and federated contexts. The VSIM dataset fills a gap in AV data diversity, providing a valuable resource for advancing real-time object detection in distributed learning applications.</p> <p> </p>
Data from: Unmanned aerial vehicles for high-throughput phenotyping and agronomic research
Advances in automation and data science have led agriculturists to seek real-time, high-quality, high-volume crop data to accelerate crop improvement through breeding and to optimize agronomic practices. Breeders have recently gained massive data-collection capability in genome sequencing of plants. Faster phenotypic trait data collection and analysis relative to genetic data leads to faster and better selections in crop improvement. Furthermore, faster and higher-resolution crop data collection leads to greater capability for scientists and growers to improve precision-agriculture practices on increasingly larger farms; e.g., site-specific application of water and nutrients. Unmanned aerial vehicles (UAVs) have recently gained traction as agricultural data collection systems. Using UAVs for agricultural remote sensing is an innovative technology that differs from traditional remote sensing in more ways than strictly higher-resolution images; it provides many new and unique possibilities, as well as new and unique challenges. Herein we report on processes and lessons learned from year 1—the summer 2015 and winter 2016 growing seasons–of a large multidisciplinary project evaluating UAV images across a range of breeding and agronomic research trials on a large research farm. Included are team and project planning, UAV and sensor selection and integration, and data collection and analysis workflow. The study involved many crops and both breeding plots and agronomic fields. The project's goal was to develop methods for UAVs to collect high-quality, high-volume crop data with fast turnaround time to field scientists. The project included five teams: Administration, Flight Operations, Sensors, Data Management, and Field Research. Four case studies involving multiple crops in breeding and agronomic applications add practical descriptive detail. Lessons learned include critical information on sensors, air vehicles, and configuration parameters for both. As the first and most comprehensive project of its kind to date, these lessons are particularly salient to researchers embarking on agricultural research with UAVs.
CAVEMOVE: An acoustic database for the study of voice-enabled technologies inside moving vehicles
<p>We provide a collection of multichannel audio recordings obtained inside four different cars. The recording process involves (i) recordings of acoustic impulse responses, which are acquired at static conditions and provide the means for modeling the speech and car-audio components (ii) recordings of acoustic noise at a wide range of both static and in-motion conditions. Data is recorded with two different microphone configurations and particularly (i) a compact microphone array or (ii) a distributed microphone setup. A <a href="https://github.com/SPL-FORTH-ICS/CAVEMOVE">python API and a Matlab API</a>, that can be freely downloaded from CAVEMOVE github, is provided as the means to easily exploit the open access audio recordings to synthesize mixtures of speech and acoustic noise at different driving conditions. This way, the user can easily synthesize the microphone signals required for research on voice enabled technologies inside moving vehicles.</p> <p>All audio recordings and impulse responses are provided at 16 kHz sampling rate and are in the form of 8-channel .wav files.</p> <p>Some basic principles followed in CAVEMOVE APIs are the following. <br>- We provide functions for retrieving speech and noise components as separate entities (e.g. numpy arrays). Users must then add the speech and noise components to derive a mixture.<br>- Noise recordings are derived as a function of driving conditions, specifically the speed (in km/hour) and the window aperture (3 or 4 different windows conditions are considered in each vehicle)<br>-Apart from the basic noise components, we also provide means for adding ventilation/air-condition noise and also, interference from the built-in car audio system (e.g. radio, cd player etc)<br>-To produce the speech components, users must provide their own dry speech recordings <br>-To produce the car-audio components, users must provide their own audio signals.</p> <p>The Documentation .pdf file that we provide along with the audio recordings lists all the conditions that were recorded or measured inside the three cars (the same documantation can also be found in CAVEMOVE github). This information is important for correct use of the python API, since, asking for a condition that was not recorded can potentially produce an error. Note that a list of recorded driving conditions given the car name and the microphone configuration can also be retrieved from auxiliary functions included in the APIs.</p> <p>For any questions with respect to CAVEMOVE dataset or API, feel free to send an email to <br>Andreas Symiakakis at andrysmi@ics.forth.gr <br>or<br>Nikos Stefanakis at nstefana@ics.forth.gr</p> <p>CAVEMOVE project is funded by the Institute of Computer Science of the Foundation for Research and Technology-Hellas (FORTH).</p>
FIGURE 7 in Deep-water decapod crustaceans studied with a remotely operated vehicle (ROV) in the Marquesas Islands, French Polynesia (Crustacea: Decapoda)
FIGURE 7. Brachyuran crabs photographed with ROV Super Achille: a) Daldorfia sp., stn 32, Nuku Hiva, 176 m; b) Garthambrus stellata (Rathbun, 1906), stn 32, Nuku Hiva, 363 m, on a rock at base of a scleractinian coral Madrepora sp.; c–d) Chaceon poupini Manning, 1992, stn 25, Dumont d'Urville Seamount, 526–535 m.
FIGURE 6 in Deep-water decapod crustaceans studied with a remotely operated vehicle (ROV) in the Marquesas Islands, French Polynesia (Crustacea: Decapoda)
FIGURE 6. Brachyuran crabs photographed with ROV Super Achille: a–b) Latreillia metanesa Williams, 1982, stn 37, Eiao, 214 m, on antipatharian coral Antipathes? sp.; c) Naxioides vaitahu Poupin, 1995 (with a specimen of L. metanesa, top), stn 37, Eiao, 214 m, on antipatharian coral Antipathes? sp.; d) Tanaoa serenei (Richer de Forges, 1983), stn 34, Hatu Iti, 334 m (distance between the two laser green spots is 60 mm).
FIGURE 4 in Deep-water decapod crustaceans studied with a remotely operated vehicle (ROV) in the Marquesas Islands, French Polynesia (Crustacea: Decapoda)
FIGURE 4. Lobsters photographed with ROV Super Achille: a) Enoplometopus crosnieri Chan & Yu, 1998, stn 16, Fatu Hiva, 204 m; b) Palinustus unicornutus Berry, 1979, stn 37, Eiao, 242 m; c–d) Puerulus sp. Chan et al. (in press), stn 36, Eiao, 227 m.
FIGURE 5 in Deep-water decapod crustaceans studied with a remotely operated vehicle (ROV) in the Marquesas Islands, French Polynesia (Crustacea: Decapoda)
FIGURE 5. Anomurans photographed with ROV Super Achille (distance between the two laser green spots is 60 mm): a) Babamunida hystrix (Macpherson & de Saint Laurent, 1991), stn 16, Fatu Hiva, 179 m; b) Bathynarius pacificus Forest, 1993, stn 37, Eiao, 242 m; c) Paragiopagurus bougainvillei (Lemaitre, 1994), stn 37, Eiao, 188 m; d) Strigopagurus poupini Forest, 1995, stn 34, Hatu Iti, 267 m.
FIGURE 3 in Deep-water decapod crustaceans studied with a remotely operated vehicle (ROV) in the Marquesas Islands, French Polynesia (Crustacea: Decapoda)
FIGURE 3. Shrimps photographed by ROV Super Achille: a) Aristaeopsis edwardsiana (Johnson, 1867), stn 16, Fatu Hiva, 524 m; b) Stenopus pyrsonotus Goy & Devaney, 1980, stn 32, Nuku Hiva, 129 m; c) Heterocarpus aff. ensifer A. Milne- Edwards, 1881, stn 32, Nuku Hiva, 380 m (distance between two laser green spots is 60 mm); d) Plesionika flavicauda Chan & Crosnier, 1991, stn 16, Fatu Hiva, 164 m.
FIGURE 2 in Deep-water decapod crustaceans studied with a remotely operated vehicle (ROV) in the Marquesas Islands, French Polynesia (Crustacea: Decapoda)
FIGURE 2. ROV stations in the Marquesas Islands, French Polynesia, during the AAMP expedition, leg 3, January 2012. Stations numbers are listed in Table 1.
FIGURE 8 in Deep-water decapod crustaceans studied with a remotely operated vehicle (ROV) in the Marquesas Islands, French Polynesia (Crustacea: Decapoda)
FIGURE 8. Brachyuran crabs collected with ROV Super Achille: a–b) Calocarcinus habei Takeda, 1980, stn 32, Nuku Hiva, 363 m, dorsal (a) and ventral (b) views (MNHN field number LC394); c–d) Quadrella aff. coronata Dana, 1852, stn 16, Fatu Hiva, 315–340 m, c) ovigerous female, dorsal view (MNHN field number LC169), d) specimen on a scleractinian coral Madracis sp. (MNHN field number LC281). a–c, photos J. Poupin, d) photo J. Starmer.
FIGURE 1 in Deep-water decapod crustaceans studied with a remotely operated vehicle (ROV) in the Marquesas Islands, French Polynesia (Crustacea: Decapoda)
FIGURE 1. Equipment used for in situ observations between 50–550 m during the AAMP expedition to the Marquesas. a) R/ V Braveheart, 39 m, at Fatu Hiva Island. The ROV is on the stern, under the gantry crane; the control cabin and remote video processing equipment are in the grey container, on the upper deck (photo J. Poupin); b) ROV Super Achille in its cage during a recovery operation. Organisms collected with the articulated arm are stored in the iron basket visible on the side of the ROV cage; the leash that links the cage to the ROV is 70 m long and it is wound on top of the cage (photo P. Chevaldonné); c) ROV out of its cage during a pre-dive at stn 19 (photo T. Pérez); d) Screen photograph taken during dive at stn 25, showing information available for each dive: course of R/V, latitude, longitude, depth, station number, island (photo COMEX).
V2X Datasets - Accidents between Passenger Vehicles and Motorcycles
<p><strong>For more details, please refer to:</strong></p> <p><strong>Bruno Ribeiro, Maria João Nicolau, and Alexandre Santos. "Using machine learning on v2x communications data for vru collision prediction." <em>Sensors</em> 23.3 (2023): 1260.</strong></p> <p>A compilation of VANET datasets collected from simulations (VEINS, coupling SUMO and OMNeT++), containing accidents between passenger vehicles and motorcycles on an intersection (two different scenarios).</p> <p>The datasets consist on V2X messages with the following information: <br>NodeID, Sender Position X, Sender Position Y, Sender Position Z, Sender Speed, Sender Heading, Sender Acceleration, Sender Vehicle Length, Sender Vehicle Width, Timestamp, Sender Vehicle Type, Accident [Bool]</p>
Automated Vehicles
<p><em><strong>In the first Rebalance Dialogue, <a href="https://rebalancemobility.eu/andrea-ricci/">Andrea Ricci</a> moderated a conversation between <a href="https://rebalancemobility.eu/ghadir-pourhashem/">Ghadir Pourhashem</a> and <a href="https://rebalancemobility.eu/cristina-pronello/">Cristina Pronello</a> about how Automated vehicles (AV) are expected to release people from the technical constraint of driving and allow people to do multiple tasks at the same time.</strong></em></p> <p>Under the assumption that a cultural shift is needed before the massive adoption of AV, REBALANCE has identified, among others, a variety of ingrained cultural and value-driven attitudes that is likely to play a fundamental role in the future of AV, beyond their technological performance: fear of innovation, fear of privacy breaches, fear of losing control, impoverishment of the human dimension of the travel experience, and ethical issues.</p> <p>During the conversation, many questions arose about whether and how to address these factors in order to impel people towards cultural shifts that would facilitate the uptake of AV. Forceful policies or nudges might initiate a slippery slope towards the dangers of an “ethical state”.</p> <p>The discussants agreed that freedom and control are two major concepts that come into play when considering people’s reliance on automation. Passivity can easily be associated with a diminished experience of freedom or loss of control. One of the most exploited arguments to overcome and compensate for this distrust is the alleged increase in road safety.</p> <blockquote> <p>The promised environmental benefits of driverless vehicles often come by the hand of shared mobility. This innovative duo might become a successful symbiotic couple or, on the contrary, this partnership could hinder their diffusion.</p> </blockquote> <p>According to the participants, the impact of vehicle automation on social inclusiveness remains uncertain. Further isolation and alienation cannot be ruled out. The paragon of the currently observed effects of COVID-19 on mobility choices might be valid once dictated whether they are transitory or permanent.</p> <p>Regarding the technological aspect and the scepticism to adopt new technologies because of lack of experience (or knowledge), the doubt in the minds of the participants appeared when considering that most technologically innovative solutions for social and environmental sustainability are mainly patching problems created by previous technological innovation. Technologies are created for doing business and not for solving problems. AV or Electric vehicles are just an attempt by the automotive sector to stay alive. Until the identification of the outset of technological progress that intrinsically leads us to sustainability, current prevailing values (such as efficiency, speed, cost savings, technological progress “per se”) perpetuate this headlong flight. The integration of technological progress will have to deal with two sets of goals, which are incompatible, or at least partly in contrast with one another: to increase speed and efficiency (cost, energy, time…); to increase comfort, safety and quality of life.</p> <p>The younger generations are shifting priority values, but it is not clear yet how this translates into the adoption of technological innovation and, particularly in the case of AVs.</p> <p>Then the conversation dealt with several topics regarding AV reliability such as misconceptions and incoherence about the use of time in AV/public transport. In that sense,</p> <blockquote> <p><strong>the rejection of AV might not be related to fear of innovation but to the impossibility to reproduce human thinking and moral decisions that bring no confidence in the machine. Socialisation and conviviality thanks to AV goes with many question marks (gender, age gap).</strong></p> </blockquote> <p>In the domains of privacy and personal data, we might find privacy issues with personal data and sharing technologies. Unfortunately, no data are publicly available for innovations and research.</p> <p>Aspirational values come into play when recognizing that the most important trip one person does is associated with emotion and pleasure. Therefore, the pleasure of driving or the preference for driving oneself can also be related to fear to change habits. There could be a confrontation between improvement of quality of life versus optimisation and misperceived opinions as facts. Maybe social inclusion will not come by sharing.</p> <p>Governance raised different points in the dialogue such as confidence of the public in policy-makers, the way of presenting to the public possible options (data, conclusions…) and targeted nudges.</p> <p>Finally, other factors agreed by the discussants that could hinder the adoption of new technologies are accidents and failures of self-driving vehicles, the fear of innovation, and ethical issues.</p>
Modelling and simulating age-dependent pedestrian behaviour with an autonomous vehicle
<p>Video "1_SimulationWithoutAgel" shows the simulation before the modifications of the model and the implementation.</p> <p>Video "2_SimulationWithAge" shows the simulation after the modifications of the model and the implementation depending on the age data.</p> <p> </p> <p>Videos of the article: "Modelling and simulating age-dependent pedestrian behaviour with an autonomous vehicle"</p> <p>Abstract: In shared spaces, autonomous vehicles (AVs) will have to move efficiently and safely, without normal road signage, and with other users such as pedestrians, cyclists and drivers. To achieve this, AVs need to anticipate the behaviours of other road users in order to adapt their navigation accordingly. This paper focuses on age-related pedestrian behaviours with an autonomous vehicle. Looking at age as one of the main factors determining behaviour, a literature review is conducted. The results are used to integrate age-dependent pedestrian behaviours into a model for simulating more realistic pedestrian behaviours in shared spaces with an AV.</p>
Vehicle Environment Dataset
<p>We collected the data from ten drivers that drove vehicles in St. Petersburg, Russia, for a few months. The image size from the road cameras is 480x640. For training, we scaled them down to 420x420 and applied center cropping to a 416x416 area to exclude border areas that contain noise and distortion. To annotate the data, we used pseudo-labeling and an ensemble of different open-source models that were trained on the KITTI dataset. The ensemble is based on a weighted mean average using the following weights [0.4, 0.3, 0.2, 0.1] from top to bottom. For each image in the dataset, we used the following four models (LapDept, DTP Hybrid, BTS, and VNL) to obtain the predictions. After that, we took the weighted average between all four masks and saved the results as our ground truth.</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.