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.

datasets available to search

ShareScore release 0.9.0

Dataset results

23 results for “Vehicle Detection”

Learn how ShareScore rates datasets ↗

zenodo48/100

Aerial Multi-Vehicle Detection Dataset

Aerial Multi-Vehicle Detection Dataset: Efficient road traffic monitoring is playing a fundamental role in successfully resolving traffic congestion in cities. Unmanned Aerial Vehicles (UAVs) or drones equipped with cameras are an attractive proposition to provide flexible and infrastructure-free traffic monitoring. Due to the affordability of  such drones, computer vision solutions for traffic monitoring have been widely used. Therefore, this dataset provide images that can be used for either training or evaluating Traffic Monitoring applications. More specifically, it can be used for training an aerial vehicle detection algorithm, benchmark an already trained vehicle detection algorithm, enhance an existing dataset and aid in traffic monitoring and analysis of road segments.  The dataset construction involved manually collecting all aerial images of vehicles using UAV drones and manually annotated into three classes 'Car', 'Bus', and ''Truck'.The aerial images were collected through manual flights in road segments in Nicosia or Limassol, Cyprus, during busy hours. The images are in High Quality, Full HD (1080p) to 4k (2160p) but are usually resized before training. All images were manually annotated and inspected afterward with the vehicles that indicate 'Car' for small to medium sized vehicles, 'Bus' for busses, and 'Truck' for large sized vehicles and trucks. All annotations were converted into VOC and COCO formats for training in numerous frameworks. The data collection took part in different periods, covering busy road segments in the cities of Nicosia and Limassol in Cyprus. The altitude of the flights varies between 150 to 250 meters high, with a top view perspective. Some of the images found in this dataset are taken from Harpy Data dataset [1]  The dataset includes a total of 9048 images of which 904 are split for validation, 905 for testing, and the rest 7239 for training.  <table> <tbody> <tr> <td>Subset</td> <td>Images</td> <td>Car</td> <td>Bus</td> <td>Truck</td> </tr> <tr> <td>Training</td> <td>7239</td> <td>200301</td> <td>1601</td> <td>6247</td> </tr> <tr> <td>Validation</td> <td>904</td> <td>23397 </td> <td>193 </td> <td>727</td> </tr> <tr> <td>Testing</td> <td>905</td> <td>24715</td> <td>208</td> <td>770</td> </tr> </tbody> </table> It is advised to further enhance the dataset so that random augmentations are probabilistically applied to each image prior to adding it to the batch for training. Specifically, there are a number of possible transformations such as geometric (rotations, translations, horizontal axis mirroring, cropping, and zooming), as well as image manipulations (illumination changes, color shifting, blurring, sharpening, and shadowing).   [1] Makrigiorgis, R., 2021. Harpy Data Dataset. [online] Kios.ucy.ac.cy. Available at: <https://www.kios.ucy.ac.cy/harpydata/> [Accessed 22 September 2022].   **NOTE** If you use this dataset in your research/publication please cite us using the following : <blockquote> Rafael Makrigiorgis, Panayiotis Kolios, & Christos Kyrkou. (2022). Aerial Multi-Vehicle Detection Dataset (1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7053442 </blockquote>

opencc-by-4.0Sep 2022View details →

zenodo44/100

Roundabout Aerial Images for Vehicle Detection

If you use this dataset, please cite this paper: Puertas, E.; De-Las-Heras, G.; Fernández-Andrés, J.; Sánchez-Soriano, J. Dataset: Roundabout Aerial Images for Vehicle Detection. Data 2022, 7, 47. https://doi.org/10.3390/data7040047 This publication presents a dataset of Spanish roundabouts aerial images taken from an UAV, along with annotations in PASCAL VOC XML files that indicate the position of vehicles within them. Additionally, a CSV file is attached containing information related to the location and characteristics of the captured roundabouts. This work details the process followed to obtain them: image capture, processing and labeling. The dataset consists of 985,260 total instances: 947,400 cars, 19,596 cycles, 2,262 trucks, 7,008 buses and 2,208 empty roundabouts, in 61,896 1920x1080px JPG images. These are divided into 15,474 extracted images from 8 roundabouts with different traffic flows and 46,422 images created using data augmentation techniques. The purpose of this dataset is to help research on computer vision on the road, as such labeled images are not abundant. It can be used to train supervised learning models, such as convolutional neural networks, which are very popular in object detection.   <table align="center"> <tbody> <tr> <td> Roundabout (scenes) </td> <td> Frames </td> <td> Car </td> <td> Truck </td> <td> Cycle </td> <td> Bus </td> <td> Empty </td> </tr> <tr> <td> 1 (00001) </td> <td> 1,996 </td> <td> 34,558 </td> <td> 0 </td> <td> 4229 </td> <td> 0 </td> <td> 0 </td> </tr> <tr> <td> 2 (00002) </td> <td> 514 </td> <td> 743 </td> <td> 0 </td> <td> 0 </td> <td> 0 </td> <td> 157 </td> </tr> <tr> <td> 3 (00003-00017) </td> <td> 1,795 </td> <td> 4822 </td> <td> 58 </td> <td> 0 </td> <td> 0 </td> <td> 0 </td> </tr> <tr> <td> 4 (00018-00033) </td> <td> 1,027 </td> <td> 6615 </td> <td> 0 </td> <td> 0 </td> <td> 0 </td> <td> 0 </td> </tr> <tr> <td> 5 (00034-00049) </td> <td> 1,261 </td> <td> 2248 </td> <td> 0 </td> <td> 550 </td> <td> 0 </td> <td> 81 </td> </tr> <tr> <td> 6 (00050-00052) </td> <td> 5,501 </td> <td> 180,342 </td> <td> 1420 </td> <td> 120 </td> <td> 1376 </td> <td> 0 </td> </tr> <tr> <td> 7 (00053) </td> <td> 2,036 </td> <td> 5,789 </td> <td> 562 </td> <td> 0 </td> <td> 226 </td> <td> 92 </td> </tr> <tr> <td> 8 (00054) </td> <td> 1,344 </td> <td> 1,733 </td> <td> 222 </td> <td> 0 </td> <td> 150 </td> <td> 222 </td> </tr> <tr> <td> Total </td> <td> 15,474 </td> <td> 236,850 </td> <td> 2,262 </td> <td> 4,899 </td> <td> 1,752 </td> <td> 552 </td> </tr> <tr> <td> Data augmentation </td> <td> x4 </td> <td> x4 </td> <td> x4 </td> <td> x4 </td> <td> x4 </td> <td> x4 </td> </tr> <tr> <td> Total </td> <td> 61,896 </td> <td> 947,400 </td> <td> 9048 </td> <td> 19,596 </td> <td> 7,008 </td> <td> 2,208 </td> </tr> </tbody> </table>

opencc-by-4.0Mar 2022View details →

zenodo40/100

Livorno, Urban driving, Connected vehicle detects fallen bicyle

Scenario description: Test session for fallen bicycle with connected but not automated vehicle Session description: The fallen bicycle use case aims to demonstrate the possibility for a vehicle to detect in advance, using V2X communication, the presence of a fallen bicycle on the road. In case of fall, the bicycle signals its presence to the other vehicles using DENM messages. Datasets descriptions: AUTOPILOT_Livorno_UrbanDriving_Vehicle_all: Data generated from the vehicle sensors This dataset refers to the vehicle datasets generated from the vehicle sensors during Urban Driving in Livorno. This includes the data coming from the CAN bus and GPS. It includes following kind of dataset: Vehicle: general data (speed, battery); PositioningSystem: data from GPS; VehicleDynamics: data about dynamic (acceleration...); LateralControl: steering and lane control data AUTOPILOT_Livorno_UrbanDriving_V2X_all: V2V messages during platooning sessions This dataset refers to the V2V messages exchanged between ITS stations (vehicles and RSUs) during the Urban Drining in Livorno. AUTOPILOT_Livorno_UrbanDriving_IoT_all: Data extracted from IoT oneM2M platform This dataset refers to messages exchanged by Urban Driving devices, applications and services across the oneM2M platform.

opencc-by-4.0Jan 2020View details →

zenodo40/100

Livorno, Urban driving, Automated vehicle detects fallen bicycle

Scenario description: Test session for AD+connected car and connected cars approaching a fallen bicycle. Session description: The fallen bicycle use case aims to demonstrate the possibility for a vehicle to detect in advance, using V2X communication, the presence of a fallen bicycle on the road. In case of fall, the bicycle signals its presence to the other vehicles using DENM messages. The AD car publishes the detected event to the oneM2M and safely reduces its speed until to stop. Goal is to record data for the technical evaluation. Datasets descriptions: AUTOPILOT_Livorno_UrbanDriving_Vehicle_all: Data generated from the vehicle sensors This dataset refers to the vehicle datasets generated from the vehicle sensors during Urban Driving in Livorno. This includes the data coming from the CAN bus and GPS. It includes following kind of dataset: Vehicle: general data (speed, battery); PositioningSystem: data from GPS; VehicleDynamics: data about dynamic (acceleration...); LateralControl: steering and lane control data AUTOPILOT_Livorno_UrbanDriving_V2X_all: V2V messages during platooning sessions This dataset refers to the V2V messages exchanged between ITS stations (vehicles and RSUs) during the Urban Drining in Livorno. AUTOPILOT_Livorno_UrbanDriving_IoT_all: Data extracted from IoT oneM2M platform This dataset refers to messages exchanged by Urban Driving devices, applications and services across the oneM2M platform.

opencc-by-4.0Jan 2020View details →

zenodo40/100

Next-generation 3D object detection and tracking for self-driving vehicles using object velocity

The synthetic dataset was generated using KITTI-like specifications and annotations format. It is comprised by the training and testing sets, that include KITTI standard  folders: label_2, image_2 and calib. Furthermore, there is a velodyne file for each of the following use cases:<ul><li>Point cloud 1: (x,y,z, (Float)Radial_Velocity): this point cloud has the relative radial velocity as an additional feature for each point. File: velodyne_radial_velocity;</li><li>Point cloud 2: (x,y,z,(Float)Absolute_Speed): in this point cloud, every point has the absolute speed of the object as the additional feature. File: velodyne_abs_speed;</li><li>Point cloud 3: (x,y,z,(Bool)Is_Moving): the additional feature of this point cloud is a Boolean value that is set to 1.0 if the object is moving; contrariwise, it is set to 0.0 for static objects. File: velodyne_is_moving;</li><li>Point cloud 4: (x,y,z,0): no additional feature information. If desired, requires post-processing to convert to (x,y,z) or changing the toolbox point cloud configuration to not consider the additional feature. File: velodyne_xyz;</li></ul>Additionally, the detections generated with the OpenPCDet toolbox and Second-IoU model are provided.This work was made as part of a master thesis of Informatics Engineering in the University of Aveiro.

opencc-by-4.0Oct 2023View details →

zenodo40/100

GPS Location Spoofing Attack Detection for Enhancing the Security of Autonomous Vehicles (presentation video)

Video of the presentation for the publication M. Kamal, A. Barua, C. Vitale, C. Laoudias and G. Ellinas, "GPS Location Spoofing Attack Detection for Enhancing the Security of Autonomous Vehicles," 2021 IEEE 94th Vehicular Technology Conference (VTC2021-Fall), 2021, pp. 1-7, doi: 10.1109/VTC2021-Fall52928.2021.9625567.

opencc-by-4.0May 2022View details →

zenodo40/100

HIT-UAV: A high-altitude infrared thermal dataset for Unmanned Aerial Vehicle-based object detection

Add citation file.

opencc-zeroFeb 2023View details →

zenodo40/100

PoqueiraVehicleLPR: A Dataset of Vehicle Detection Sensors in the region of Barranco de Poqueira in the Alpujarra Granadina.

This dataset is linked to the analysis of different aspects related to the conservation of the Sierra Nevada National Park through advanced digital systems. The devices have been deployed along the road that passes through the municipalities of Pampaneira, Bubión and Capileira, in the Alpujarra region of Granada. Data is collected by 4 devices equipped with vehicle detection sensors. These devices are Hikvision LPR IP cameras with Automatic number-plate recognition (ANPR) based on Deep Learning. The devices have a 2MP resolution, 2.8-12 mm varifocal optics, and IR LEDs with a range of 50 m. To cover the entrances and exits of each village in the target area, we strategically positioned the cameras. The locations are entrance to Pampaneira from the western part of the Alpujarra (PAM1), entrance to Pampaneira from the eastern part of the Alpujarra (PAM2), entrance to Bubión via a single road (BUB), and entrance to Capileira via a single road (CAP).  The attached data in the CSV files DATA_VEHICLES_2022 and DATA_VEHICLES_2023 contain information about vehicle passages in the years 2022 (from February to December) and 2023 (from January to August) for each installed camera. It includes anonymized license plate information based on an identifier to facilitate cross-referencing and in-depth analysis. The collected variables include: <ul> <li> camera_ID: License Plate Recognition (LPR) camera identifier. </li> <li> date: Timestamp indicating the date and time of the vehicle passage through the camera. </li> <li> num_plate_id: Anonymized license plate identifier. A value of -1 indicates that the vehicle was not correctly identified by the camera. </li> <li> direction: Binary value (IN/OUT) indicating whether the vehicle is entering or exiting the municipality referenced by the camera. </li> </ul>

opencc-by-4.0Sep 2023View details →

dryad36/100

Fluorescence‐based detection of field targets using an autonomous unmanned aerial vehicle system

This dataset comprises of the IDL code referenced in the 'Open Research' section of the Kaye and Pittman (2020) study 'Fluorescence‐based detection of field targets using an autonomous unmanned aerial vehicle system' published in Methods in Ecology and Evolution (<a href="https://doi.org/10.1111/2041-210X.13402">https://doi.org/10.1111/2041-210X.13402</a>). This study describes a proof‐of‐concept autonomous unmanned aerial vehicle (UAV) system that utilizes the fluorescence characteristics unique to different materials to scan and acquire targets in the field e.g. fossils, rocks and minerals, organisms and archaeological artefacts. This is possible because these targets are often highly fluorescent against lower fluorescence backgrounds and may exhibit different colours. Fluorescence is stimulated by a near‐UV laser that is projected across the ground as a horizontal line directly below the UAV. The IDL code is for laser line and colour extractions in the laser scan strip. The raw .jpeg data for the IDL code is not provided here as this depends on what target is being scanned. All image data are made available in the paper. Additional contextual information is provided in the '2 MATERIALS AND METHODS' section of the paper, especially in Figure 3.

opencc-zeroAug 2020View details →

zenodo36/100

Self-Learning Vehicle Detection Dataset for Urban Environments

This dataset was collected as part of a research study aimed at enhancing vehicle detection algorithms through a self-learning approach tailored for urban environments. The primary objective was to minimize dependency on extensive manual labeling and improve adaptability and effectiveness in dynamic urban conditions. The study utilized urban camera infrastructures to gather real-time traffic data, focusing on a diverse range of vehicle types. The dataset includes images captured from traffic cameras situated at the intersection of Calle de Alcalá and Calle de Velázquez in Madrid, Spain, operated by the Madrid City Council. Data collection spanned from November 30, 2023, to December 6, 2023, covering daytime traffic between 8:30 hours and 18:00 hours. A total of 770 images were captured at approximately 5-minute intervals. This dataset specifically targets five vehicle types: buses, cars, motorcycles, trucks, and vans, chosen to encompass a wide range of vehicle sizes, shapes, and functionalities commonly encountered in city traffic. A subset of 134 images was manually labeled, into sets for training, validation (fine-tuning phase), and validation (self-training phase). The remaining 653 images were labeled automatically via the self-learning process proposed in the research.

opencc-by-4.0Apr 2024View details →

zenodo36/100

Smart Battery Management System for Electric Vehicles: Selflearning Algorithms for Simultaneous State and Parameter Estimation, and Stress Detection

The project proposes to develop parameter-varying SOH-coupled models for lithium-ion battery and self-learning algorithms to learn the model for simultaneous state and parameter estimation and fault detection. The traditional battery models use constant parameters, limiting their accuracy for predicting the state of the charge and health over the complete life-cycle. In practice, the battery parameters vary with the change in the state of charge and state of health. SOH-coupled models can be used to estimate the state of charge and health accurately. Further, obtaining the model parameters is also a challenging task for designing filters or observers for state estimation. A self-learning algorithm can eliminate the requirement of the model parameters. In this project, three SOH-coupled models are proposed and validated experimentally. The models are also used to design extended Kalman filters (EKF) for the state of charge, state of health, core and surface temperature, and internal resistance estimation. The results showed that the SOHcoupled models are more effective when compared to the uncoupled models in the literature. Further, it was found that EKFs based state estimation errors were within 1%. The self-learning algorithm using a two-layer neural network showed the ability to learn the models in real-time. However, the state estimation errors are higher for the self-learning scheme compared to the EKF based approaches. This is due to the limited measurement and online training schemes utilized to train neural networks. This requires further investigation in hyper-parameter tuning for implementation. Finally, a model-based fault detection scheme was proposed to detect internal thermal fault at its onset. The SOHcoupled model is reformulated to incorporate the internal resistance as a state. The EKF is used as a fault detection observer. The proposed fault detection scheme is validated using numerical simulation. It was observed that the fault detection scheme with SOH coupled electro-thermal-aging model could effectively detect a thermal fault at its incipient state.

opencc-by-4.0Nov 2021View details →

zenodo36/100

Night and Day Instance Segmented Park (NDISPark) Dataset: a Collection of Images taken by Day and by Night for Vehicle Detection, Segmentation and Counting in Parking Areas

The Dataset A collection of images of parking lots for vehicle detection, segmentation, and counting. Each image is manually labeled with pixel-wise masks and bounding boxes localizing vehicle instances. The dataset includes about 250 images depicting several parking areas describing most of the problematic situations that we can find in a real scenario: seven different cameras capture the images under various weather conditions and viewing angles. Another challenging aspect is the presence of partial occlusion patterns in many scenes such as obstacles (trees, lampposts, other cars) and shadowed cars. The main peculiarity is that images are taken during the day and the night, showing utterly different lighting conditions. We suggest a three-way split (train-validation-test). The train split contains images taken during the daytime while validation and test splits include images gathered at night. In line with these splits we provide some annotation files: <ul> <li> train_coco_annotations.json and val_coco_annotations.json --> JSON files that follow the golden standard MS COCO data format (for more info see <a href="https://cocodataset.org/#format-data">https://cocodataset.org/#format-data</a>) for the training and the validation splits, respectively. All the vehicles are labeled with the COCO category 'car'. They are suitable for vehicle detection and instance segmentation. </li> <li> train_dot_annotations.csv and val_dot_annotations.csv --> CSV files that contain xy coordinates of the centroids of the vehicles for the training and the validation splits, respectively. Dot annotation is commonly used for the visual counting task. </li> <li> ground_truth_test_counting.csv --> CSV file that contains the number of vehicles present in each image. It is only suitable for testing vehicle counting solutions. </li> </ul>   Citing our work If you found this dataset useful, please cite the following paper <blockquote> <pre>@inproceedings{Ciampi_visapp_2021,   doi = {10.5220/0010303401850195},   url = {https://doi.org/10.5220%2F0010303401850195},   year = 2021,   publisher = {{SCITEPRESS} - Science and Technology Publications},   author = {Luca Ciampi and Carlos Santiago and Joao Costeira and Claudio Gennaro and Giuseppe Amato},   title = {Domain Adaptation for Traffic Density Estimation},   booktitle = {Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications} } </pre> </blockquote> and this Zenodo Dataset <blockquote> <pre>@dataset{ciampi_ndispark_6560823,   author = {Luca Ciampi and Carlos Santiago and Joao Costeira and Claudio Gennaro and Giuseppe Amato},   title = {{Night and Day Instance Segmented Park (NDISPark) Dataset: a Collection of Images taken by Day and by Night for Vehicle Detection, Segmentation and Counting in Parking Areas}},   month = may,   year = 2022,   publisher = {Zenodo},   version = {1.0.0},   doi = {10.5281/zenodo.6560823},   url = {https://doi.org/10.5281/zenodo.6560823} } </pre> </blockquote>   Contact Information If you would like further information about the dataset or if you experience any issues downloading files, please contact us at <a href="mailto:mobdrone@isti.cnr.it">luca.ciampi@isti.cnr.it</a>

openodc-byDec 2021View details →

zenodo36/100

Enhanced Vehicle Detection via YOLOv7-Tiny, dataset we used

Our improvement on YOLOv7-tiny, with Sim_DFC, Inner-shape IoU, and BiFPN. These are the datasets we used.

opencc-by-4.0Nov 2024View details →

zenodo36/100

Intersection Monitoring: A dataset for vehicle detection using an infrastructure camera including ground truth vehicle localization

Intersection Monitoring: A dataset for vehicle detection using an infrastructure camera including ground truth vehicle localization. This dataset contains images from a infrastructure camera monitoring an intersection and the ground-truth information for a vehicle crossing it from different directions. The data is aimed to develop and improve image-based vehicle detection algorithms. The dataset includes two different recordings with the same structure. For each of them, the sequence of images is provided in PNG format, along with the ground truth of the vehicle. The ground truth data was captured using a high-precision GNSS receiver installed on the test vehicle, fused with in-vehicle sensors using an Extended Kalman Filter (EKF) . Time considerations The camera and GNSS receiver clocks were synchronized before each test to have the same time base. Each test last about 140 seconds. Image files Image files can be found on the img/ folder within for each test. The camera was configured to record images at 25 fps: <ul> <li>Test 1: 3704 files</li> <li>Test 2: 3426 files</li> </ul> Vehicle localization ground truth The test vehicle is a prototype of Autonomous Vehicle developed by the <a href="https://autopia.car.upm-csic.es">AUTOPIA</a> research group at the <a href="https://car.upm-csic.es">Centre for Automation and Robotics</a> in Spain. Vehicle location mainly depends on a Trimble BX982 GNSS receiver using RTK inputs from a local station. However, the location algorithm applies an EKF for combining GNSS measurements with different onboard sensors providing yaw rate, longitudinal acceleration and speed, steering wheel position and speed, etc. For each test, the vehicle.csv file contains the vehicle information recorded at 20Hz. This file includes: <ul> <li>UTM Time: Time using the format HHMMSSss: <ul> <li>HH: Hours</li> <li>MM: Minutes</li> <li>SS: Seconds</li> <li>ss: Fraction of seconds</li> </ul> </li> <li>UTM East: East coordinate of the GNSS antenna in the UTM frame, in meters.</li> <li>UTMNorth: North coordinate of the GNSS antenna in the UTM frame, in meters.</li> <li>Orientation: Yaw angle of the vehicle, measured from the East axis (x-axis).</li> <li>Speed: Vehicle speed in m/s</li> <li>Acceleration: Vehicle acceleration in m/s^2</li> </ul> Camera info The file camera_parameters.json includes all the information about the intrinsic and extrinsic parameters for the camera. The configuration stored on this file appplies to all tests. The camera used is an AXIS M1125 with variable focal length. It was installed in a communication tower near the intersection. Vehicle info The file vehicle_parameters.json includes information about vehicle dimensions and antenna location. The GNSS antenna is installed near the rear axle of the vehicle, in the middle part of the vehicle. The configuration stored on this file appplies to all tests. Tools Some MATLAB tools can be found in <a href="https://github.com/autopia-car/datasets-tools-intersection-monitoring">https://github.com/autopia-car/datasets-tools-intersection-monitoring</a> Disclaimer That the dataset comes "AS IS", without express or implied warranty and/or any liability exceeding mandatory statutory obligations. This especially applies to any obligations of care or indemnification in connection with the dataset. The dataset was created for our research purposes only and no quality assessment was done for the usage in products of any kind. We can therefore not guarantee for the correctness, completeness or reliability of the provided data set.

opencc-by-4.0Mar 2023View details →

dryad36/100

Fluorescence‐based detection of field targets using an autonomous unmanned aerial vehicle system

Open the record for dataset details and reuse information.

publicAug 2020View details →

zenodo32/100

Dataset for Detecting Vehicle in Pedestrian Areas version 2

The Car_Truck_Bus_Pedestrian-Area_v2.zip is an updated collection featuring a greater number of images, specifically 7808 images, each in very high resolution in .jpg format. The total file size is now 290 MB. It continues to serve the purpose of detecting vehicles in pedestrian areas within urban environments and is captured at a resolution of 1280×720 (HD). Each image is approximately 58 KB in size. The image data was collected from 100 strategically placed public CCTVs in Medellín, Colombia, under various light and weather conditions, recorded every 60 seconds between 8:00 a.m. and 3:00 p.m. For each image, it is necessary to identify cars, buses, trucks, and pedestrians in particular zones, differentiated from the background. This enhanced dataset aims to train and evaluate machine learning models for urban traffic management and pedestrian safety applications. Data in this document is published under the Creative Commons Attribution 4.0 International License.

opencc-by-4.0Jun 2024View details →

zenodo32/100

BadODD: Bangladeshi Autonomous Vehicle Object Detection Dataset

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.

opencc-by-4.0Jan 2024View details →

zenodo28/100

A Fine-Grained Vehicle Detection (FGVD) Dataset for Unconstrained Roads

The previous fine-grained datasets mainly focus on classification and are often captured in a controlled setup, with the camera focusing on the objects. We introduce the first Fine-Grained Vehicle Detection (FGVD) dataset in the wild, captured from a moving camera mounted on a car. It contains 5502 scene images with 210 unique fine-grained labels of multiple vehicle types organized in a three-level hierarchy. While previous classification datasets also include makes for different kinds of cars, the FGVD dataset introduces new class labels for categorizing two-wheelers, autorickshaws, and trucks. The FGVD dataset is challenging as it has vehicles in complex traffic scenarios with intra-class and inter-class variations in types, scale, pose, occlusion, and lighting conditions. The current object detectors like yolov5 and faster RCNN perform poorly on our dataset due to a lack of hierarchical modeling. Along with providing baseline results for existing object detectors on FGVD Dataset, we also present the results of a combination of an existing detector and the recent Hierarchical Residual Network (HRN) classifier for the FGVD task. Finally, we show that FGVD vehicle images are the most challenging to classify among the fine-grained datasets.

opencc-by-4.0Dec 2022View details →

zenodo28/100

A Fine-Grained Vehicle Detection (FGVD) Dataset for Unconstrained Roads

opencc-by-4.0Dec 2022View details →

ClinicalTrials.gov24/100

Early Detection of Selected Neuropathologies in Motor Vehicle Drivers

ClinicalTrials.gov study NCT07360886. IPD Sharing: NO. Countries: 1. Publications: 0.

closedIPD-NOFeb 2026View details →

ScienceDex guides

Understand access before you commit

These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.

Compare curated 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.

allen-brain-atlas

neuroscienceopenDocumentation, web resources, and API references are available online.

Last verified 2026-04-30Open record

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.

abode-home-cage

behavioral-neuroscienceopenThe DataShare record exposes download links for annotations, documentation, license text, and the zipped per-snippet data directory.

Last verified 2026-04-30Open record

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.

dandi-nwb

electrophysiologyopenPublished Dandiset metadata and archive endpoints are available through the production DANDI API.

Last verified 2026-04-30Open record

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.

ibl

behavioral-neuroscienceopenPublic sessions can be searched and loaded from the IBL public data server through ONE.

Last verified 2026-04-29Open record

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.

openneuro

neuroscienceopenPublished datasets are available on demand over the internet.

Last verified 2026-04-29Open record