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.
6
datasets available to search
ShareScore release 0.7.1
Dataset results
6 results for “Obstacle detection”
Benchmark for energy efficient obstacle detection on head mounted wearable for the vision impaired
<p>Here we present a novel benchmark dataset with the associated challenge, that is to detect obstacles based on head-mounted sensors and lightweight wearable devices to assist Blind and Visually Impaired individuals (BVIs) navigate in indoor environments. The challenge encompasses three objectives: (1) as accurately as possible to detect the obstacles on the pathway that likely lead to a collision; (2) as durably as possible on a given amount of battery power for the detection algorithm or model to run; (3) as reliably as possible to compensate natural head turns so nearby objects would not trigger false alarms. The data provided in the benchmark are collected from the following head mounted sensors: (i) nine low-cost ultrasonic sensors; (ii) one high-end ultrasonic sensor with a larger detection range but higher power consumption; (iii) a 9-Degrees of Freedom (DOF) Inertial Measurement Unit (IMU). The resulting dataset consists of more than 188,000 unique sequences obtained from multiple subjects walking in three different indoor scenarios. This benchmark is to facilitate and encourage accurate yet fast obstacle detection solutions that can really benefit BVIs. </p>
UAV Railroad Images for Segmentation and Obstacle Detection
<p><span>UAV-RSOD dataset contains five different types of obstacles including </span><span>person, boulder, barrel, branch, jerry can, and iron rod. This dataset supports the development and evaluation of computer vision models for railroad-related applications, such as autonomous train navigation, obstacle detection in railroad, railroad extraction and safety monitoring. </span><span> </span><span>The DJI Phantom 4 PRO UAV </span><span>Drone was used to take all the videos and images in the Indian Railways, Tiruchirapalli city of Tamilnadu, India.</span></p> <p><span>Version 1: 315 Images with Labelling, Masking for Segmentation Process and without any Data Augmentation techniques applied</span></p> <p><span>Version 2: 2002 Annotated Images with Data Augmentation techniques applied (Rotate, Flip, etc) for Obstacle Detection</span></p>
Vision-Based Obstacle Detection on Rail Tracks
<p><strong>Acknowledgement and Disclaimers</strong></p> <p>These data are a product of a research activity conducted in the context of the <a href="http://rails-project.eu">RAILS (Roadmaps for AI integration in the raiL Sector) project</a>. RAILS has received funding from the Shift2Rail Joint Undertaking (JU) under the European Union’s Horizon 2020 research and innovation programme under grant agreement n. 881782 Rails. The JU receives support from the European Union’s Horizon 2020 research and innovation program and the Shift2Rail JU members other than the Union.</p> <p>The information and views set out in this description are those of the author(s) and do not necessarily reflect the official opinion of Shift2Rail Joint Undertaking. The JU does not guarantee the accuracy of the data included in this dataset. Neither the JU nor any person acting on the JU’s behalf may be held responsible for the use which may be made of the information contained therein.</p> <p>This "dataset" has been created for scientific purposes only to study the potentials of Deep Learning (DL) approaches when used to analyse Video Data in order to detect possible obstacles on rail tracks and thus avoid collisions. The authors DO NOT ASSUME any responsibility for the use that other researchers or users will make of these data.</p> <p> </p> <p><strong>Objectives of the Study</strong></p> <p>RAILS defined some pilot case studies to develop Proofs-of-Concept (PoCs), which are conceived as benchmarks, with the aim of providing insight towards the definition of technology roadmaps that could support future research and/or the deployment of AI applications in the rail sector. In this context, the main objectives of the specific PoC "Vision-Based Obstacle Detection on Rail Tracks" were to investigate: i) solutions for the generation of synthetic data, suitable for the training of DL models; and ii) the potential of DL applications when it comes to detecting any kind of obstacles on rail tracks while exploiting video data from a single RGB camera.</p> <p> </p> <p><strong>A Brief Overview of the Approach</strong></p> <p>A multi-modular approach has been proposed to achieve the objectives mentioned above. The resulting architecture includes the following modules:</p> <ul> <li>The Rails Detection Module (RDM) detects rail tracks. The output of the RDM is used by the ODM and ADM.</li> <li>The Object Detection Module (ODM) detects obstacles whose type is known in advance.</li> <li>The Anomaly Detection Module (ADM) identifies any possible anomaly on rail tracks. These include obstacles whose type is not known in advance.</li> <li>The Obstacle Detection Module merges the outputs from the ODM and the ADM.</li> <li>The Distance Estimation Module estimates the distance of objects and anomalies from the train.</li> </ul> <p>The research was specifically oriented at implementing the RDM-ADM pipeline. Indeed, the object detection approaches that would be used to implement the ODM have been widely investigated by the research community, instead, to the best of our knowledge, limited work has been done in the rails field in the context of anomaly detection. The RDM has been realised by adopting a <em>Semantic Segmentation</em> approach based on <em>U-Net</em>; while, to develop the ADM, a <em>Vector-Quantized Variational Autoencoder</em> trained in <em>Unsupervised </em>mode was leveraged. Further details can be found in the RAILS <a href="http://rails-project.eu/downloads/deliverables/">"Deliverable D2.3: WP2 Report on experimentation, analysis, and discussion of results"</a>.</p> <p> </p> <p><strong>Steps to implement the RDM-ADM pipeline and description of shared Data</strong></p> <p>The following list reports all the steps that have been performed to implement the RDM-ADM pipeline; the words in bold-italic refer to the files that are shared within this dataset:</p> <ol> <li>A Railway Scenario was generated in MathWorks' <a href="https://www.mathworks.com/products/roadrunner.html">RoadRunner</a>.</li> <li>A video (<strong><em>FreeTrackVideo</em></strong>) was recorded by simulating an RGB camera mounted in front of the train; no obstacles on rail tracks were considered in this phase.</li> <li>2000 frames (<strong><em>FreeTrack2KFrames</em></strong>) were extracted from the aforementioned video. The video contains 4143 frames, however, only 2000 (each other frame starting from the first one) were taken into account due to training time and GPU RAM constraints.</li> <li>Only 10% of the 2000 frames were manually labelled (i.e., 200 frames, a frame every 10 frames) by exploiting LabelMe; these frames were then subdivided into training and validation sets (<strong><em>InitialLabelledSet</em></strong>).</li> <li>Hence, a Semi-Automatic labelling algorithm was developed by leveraging self-training and transfer learning. This algorithm made it possible to label all the FreeTrack2KFrames starting from the InitialLabelledSet. The resulting labels can be found in <strong><em>FreeTrack2KLabels</em></strong>.</li> <li>Data Augmentation was then performed in order to introduce some aleatory in the dataset. Because of the same time and RAM constraints mentioned above, the FreeTrack2KFrames set of data was reduced further: 1600 frames were selected among the aforementioned 2000 and then 5 transformations (Bright, Dark, Rain, Shadow, and Sun Flare) were applied to obtain the dataset (<em><strong>FreeTrack16TrainSet</strong>, <strong>FreeTrack16ValSet</strong>, <strong>FreeTrack16TestSet</strong></em>) that was used to train, validate, and test the RDM.</li> <li>Once the RDM was trained, the FreeTrackVideo was processed to obtain the masked frames that were then used to build the dataset(s) to train, validate, and test the ADM. The ADM was studied by considering two different datasets: the <em>Non-Anomaly Dataset</em> (<strong><em>NAD</em></strong>), which basically contains all the frames of the FreeTrackVideo once processed by the RDM; and the <em>Augmented Non-Anomaly Dataset (<strong>A-NAD</strong>)</em>, which contains 9000 frames, 1500 of which were extracted from the NAD, while the remaining 7500 were obtained by applying the same transformations mentioned above.</li> <li>Lastly, when both the RDM and the ADM were trained, the performances of the whole RDM-ADM pipeline were tested on the <strong><em>WithCarVideo</em></strong> which depicts the same scenario as the FreeTrackVideo but it also depicts a car laying on the rail tracks (i.e., an obstacle).</li> </ol>
Signs of life detection behind obstacles using an UWB radar sensor
<p>The "Signs of life detection behind obstacles using an UWB radar sensor" dataset was created by University of West Attica, by collecting data from 9 people using an UWB sensor, which was the X4M200 UWB radar sensor by Novelda, with and without the existence of a wall between the subject and the radar for the purposes of RESCUER project (https://rescuerproject.eu/ - a Horizon 2020 Research & Innovation Programme under Grant Agreement No.101021836). In all cases, the subject was lying down in the same stance for about 1 min and the radar was placed in four different positions: a) 0.2 m from the ground, b) 0.5 m from the ground, c) 1 m from the ground, d) 1 m from the ground and with a 45 degree angle. For comparison purposes, we also include in the dataset the case where no human is present within the radar's detection area. The subjects were placed in a distance between 0.5 and 5 metres from the radar and different stances were considered, while data were collected both for the amplitude (designated as abs) and the phase of the signal (designated as angle). This information is designated in each filename. For example, the filename "2 facing radar abs.csv", indicates that the subject is placed in 2 metres away from the radar, he/she is facing the radar and the file contains the signal's amplitude. The sampling rate of the radar was set to 17 samples per second and a distance step of about 0.05144 m was also considered.</p>
Navigation Test in Simulated Environment Rosbag. Human obstacle detection.
<p>This repository contains rosbags (ROS 2 Humble) extracted from a navigation test realized in a simulated environment (Amazon Hospital map) with an RB1 robot. The test consist of a navigation form one point to another with a human obstacle avoidance.</p> <p> </p> <p>This research is part of the project TESCAC, financed by “European Union NextGeneration-EU, the Recovery Plan, Transformation and Resilience, through INCIBE".</p>
Feasibility Test of Virtual Reality Obstacle Detection for Low Vision Walking
ClinicalTrials.gov study NCT05141604. IPD Sharing: NO. Countries: 1. Publications: 0.
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.