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.
7
datasets available to search
ShareScore release 0.7.1
Dataset results
7 results for “mapping point cloud”
Precision viticulture dataset for detailed vineyard mapping composed of geotagged smartphone ground images, phytosanitary status, UAV orthomosaics, 3D point clouds, and RTK GNSS data - Northern Spain, July 2022
<p>This dataset offers a rich multimodal collection of data from vineyards, designed to enhance agricultural research with a focus on vineyard management and disease monitoring. It includes geotagged smartphone ground images in ".7z" format for detailed plant-level analysis, a ".csv" file detailing plants' phytosanitary status for health assessment, UAV-derived 3D Point Clouds and orthomosaics in ".las" and ".tiff" formats for aerial landscape views, and RTK GNSS data in ".shp" format for precise plant geolocations.</p> <p>This dataset can be combined with other datasets to enable a comprehensive view of the vineyards and improve its value:</p> <div> <ul> <li>Ariza-Sentís, Mar, Sergio Vélez, and João Valente. ‘Dataset on UAV RGB Videos Acquired over a Vineyard Including Bunch Labels for Object Detection and Tracking’. <em>Data in Brief</em> 46 (February 2023): 108848. <a href="https://doi.org/10.1016/j.dib.2022.108848">https://doi.org/10.1016/j.dib.2022.108848</a>.</li> <li>Vélez, Sergio, Mar Ariza-Sentís, and João Valente. ‘VineLiDAR: High-Resolution UAV-LiDAR Vineyard Dataset Acquired over Two Years in Northern Spain.’ <em>Data in Brief</em>, October 2023, 109686. <a href="https://doi.org/10.1016/j.dib.2023.109686">https://doi.org/10.1016/j.dib.2023.109686</a>.</li> <li> <div> <div>Vélez, Sergio, Mar Ariza-Sentís, and João Valente. ‘Dataset on Unmanned Aerial Vehicle Multispectral Images Acquired over a Vineyard Affected by Botrytis Cinerea in Northern Spain’. <em>Data in Brief</em> 46 (February 2023): 108876. <a href="https://doi.org/10.1016/j.dib.2022.108876">https://doi.org/10.1016/j.dib.2022.108876</a>.</div> <div> </div> </div> </li> </ul> </div>
Forest metrics derived from the 2008 Lidar point clouds, includes canopy closure, percentile height, and stem mapping for the Andrews Experimental Forest.
There are three types of forest metrics within this database. They all are derived from the raw Lidar point clouds using the FUSION software. The three types are canopy closure, height metric, and stem mapping. The canopy closure and height metric grids cover a variety of canopy heights and grid cell sizes. 1. Canopy closure: This metric measures the canopy closure of a given horizontal cell above a given vertical threshold (height break). Canopy closure can inform many landscape models and provide insight on how much light will reach the forest floor. 2. Height Metric: This metric measures the height at which a given percent of the first return points are below. This analysis is done in a given grid cell size. Height metrics give various statistics of the elevation above ground for a given set of Lidar points. In forested landscapes, first return height metrics describe the forest canopy. 3.This stem map locates the approximate center of all trees in the HJ Andrews Research Forest greater than 10 meters. In addition to the stem location, a canopy radius is also provided. FUSION and TreeVaWA software programs were used to develop this data. Watershed Sciences, Inc. (WS) collected Light Detection and Ranging (LiDAR) data from HJ Andrews and the Willamette National Forest (NF) on August 10th and 11th 2008. Total area for this AOI is 17,705 acres. The total area of delivered LiDAR including 100 m buffer is 19,493 acres.
3DHD CityScenes: High-Definition Maps in High-Density Point Clouds
<p><strong>Overview</strong></p> <p>3DHD CityScenes is the most comprehensive, large-scale high-definition (HD) map dataset to date, annotated in the three spatial dimensions of globally referenced, high-density LiDAR point clouds collected in urban domains. Our HD map covers 127 km of road sections of the inner city of Hamburg, Germany including 467 km of individual lanes. In total, our map comprises 266,762 individual items.</p> <p>Our corresponding paper (published at ITSC 2022) is available <a href="https://www.researchgate.net/publication/364309881_3DHD_CityScenes_High-Definition_Maps_in_High-Density_Point_Clouds">here</a>.<br> Further, we have applied 3DHD CityScenes to map deviation detection <a href="https://www.researchgate.net/publication/368983255_DNN-Based_Map_Deviation_Detection_in_LiDAR_Point_Clouds">here</a>. </p> <p>Moreover, we release code to facilitate the application of our dataset and the reproducibility of our research. Specifically, our 3DHD_DevKit comprises:</p> <ul> <li>Python tools to read, generate, and visualize the dataset,</li> <li>3DHDNet deep learning pipeline (training, inference, evaluation) for<br> map deviation detection and 3D object detection.</li> </ul> <p>The DevKit is available here:</p> <p><a href="https://github.com/volkswagen/3DHD_devkit">https://github.com/volkswagen/3DHD_devkit</a>.</p> <p>The dataset and DevKit have been created by <a href="https://de.linkedin.com/in/christopher-plachetka-42b325115">Christopher Plachetka</a> as project lead during his PhD period at Volkswagen Group, Germany.</p> <p>When using our dataset, you are welcome to cite:</p> <pre><code>@INPROCEEDINGS{9921866, author={Plachetka, Christopher and Sertolli, Benjamin and Fricke, Jenny and Klingner, Marvin and Fingscheidt, Tim}, booktitle={2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)}, title={3DHD CityScenes: High-Definition Maps in High-Density Point Clouds}, year={2022}, pages={627-634}}</code></pre> <p><strong>Acknowledgements </strong></p> <p>We thank the following interns for their exceptional contributions to our work.</p> <ul> <li><a href="https://www.linkedin.com/in/sertolli/">Benjamin Sertolli</a>: Major contributions to our DevKit during his master thesis</li> <li>Niels Maier: Measurement campaign for data collection and data preparation</li> </ul> <p>The European large-scale project Hi-Drive (<a href="http://www.Hi-Drive.eu">www.Hi-Drive.eu</a>) supports the publication of 3DHD CityScenes and encourages the general publication of information and databases facilitating the development of automated driving technologies.</p> <p><strong>The Dataset</strong></p> <p>After downloading, the 3DHD_CityScenes folder provides five subdirectories, which are explained briefly in the following.</p> <p>1. Dataset</p> <p>This directory contains the training, validation, and test set definition (train.json, val.json, test.json) used in our publications. Respective files contain samples that define a geolocation and the orientation of the ego vehicle in global coordinates on the map.</p> <p>During dataset generation (done by our DevKit), samples are used to take crops from the larger point cloud. Also, map elements in reach of a sample are collected. Both modalities can then be used, e.g., as input to a neural network such as our 3DHDNet.</p> <p>To read any JSON-encoded data provided by 3DHD CityScenes in Python, you can use the following code snipped as an example.</p> <pre><code class="language-python">import json json_path = r"E:\3DHD_CityScenes\Dataset\train.json" with open(json_path) as jf: data = json.load(jf) print(data)</code></pre> <p>2. HD_Map</p> <p>Map items are stored as lists of items in JSON format. In particular, we provide:</p> <ul> <li>traffic signs,</li> <li>traffic lights,</li> <li>pole-like objects,</li> <li>construction site locations,</li> <li>construction site obstacles (point-like such as cones, and line-like such as fences),</li> <li>line-shaped markings (solid, dashed, etc.),</li> <li>polygon-shaped markings (arrows, stop lines, symbols, etc.),</li> <li>lanes (ordinary and temporary),</li> <li>relations between elements (only for construction sites, e.g., sign to lane association).</li> </ul> <p>3. HD_Map_MetaData</p> <p>Our high-density point cloud used as basis for annotating the HD map is split in 648 tiles. This directory contains the geolocation for each tile as polygon on the map. You can view the respective tile definition using QGIS. Alternatively, we also provide respective polygons as lists of UTM coordinates in JSON.</p> <p>Files with the ending .dbf, .prj, .qpj, .shp, and .shx belong to the tile definition as “shape file” (commonly used in geodesy) that can be viewed using QGIS. The JSON file contains the same information provided in a different format used in our Python API.</p> <p>4. HD_PointCloud_Tiles</p> <p>The high-density point cloud tiles are provided in global UTM32N coordinates and are encoded in a proprietary binary format. The first 4 bytes (integer) encode the number of points contained in that file. Subsequently, all point cloud values are provided as arrays. First all x-values, then all y-values, and so on. Specifically, the arrays are encoded as follows.</p> <ul> <li>x-coordinates: 4 byte integer</li> <li>y-coordinates: 4 byte integer</li> <li>z-coordinates: 4 byte integer</li> <li>intensity of reflected beams: 2 byte unsigned integer</li> <li>ground classification flag: 1 byte unsigned integer</li> </ul> <p>After reading, respective values have to be unnormalized. As an example, you can use the following code snipped to read the point cloud data. For visualization, you can use the pptk package, for instance.</p> <pre><code class="language-python">import numpy as np import pptk file_path = r"E:\3DHD_CityScenes\HD_PointCloud_Tiles\HH_001.bin" pc_dict = {} key_list = ['x', 'y', 'z', 'intensity', 'is_ground'] type_list = ['<i4', '<i4', '<i4', '<u2', 'u1'] with open(file_path, "r") as fid: num_points = np.fromfile(fid, count=1, dtype='<u4')[0] # print(num_points) # Init for k, dtype in zip(key_list, type_list): pc_dict[k] = np.zeros([num_points], dtype=dtype) # Read all arrays for k, t in zip(key_list, type_list): pc_dict[k] = np.fromfile(fid, count=num_points, dtype=t) # Unnorm pc_dict['x'] = (pc_dict['x'] / 1000) + 500000 pc_dict['y'] = (pc_dict['y'] / 1000) + 5000000 pc_dict['z'] = (pc_dict['z'] / 1000) pc_dict['intensity'] = pc_dict['intensity'] / 2**16 pc_dict['is_ground'] = pc_dict['is_ground'].astype(np.bool_) fid.close() print(pc_dict) # Visualization # Normalize (due to large UTM values) x_utm = pc_dict['x'] - np.mean(pc_dict['x']) y_utm = pc_dict['y'] - np.mean(pc_dict['y']) z_utm = pc_dict['z'] xyz = np.column_stack((x_utm, y_utm, z_utm)) viewer = pptk.viewer(xyz) viewer.attributes(pc_dict['intensity']) viewer.set(point_size=0.03)</code></pre> <p>5. Trajectories</p> <p>We provide 15 real-world trajectories recorded during a measurement campaign covering the whole HD map. Trajectory samples are provided approx. with 30 Hz and are encoded in JSON.</p> <p>These trajectories were used to provide the samples in train.json, val.json. and test.json with realistic geolocations and orientations of the ego vehicle.</p> <ul> <li>OP1 – OP5 cover the majority of the map with 5 trajectories.</li> <li>RH1 – RH10 cover the majority of the map with 10 trajectories.</li> </ul> <p>Note that OP5 is split into three separate parts, a-c. RH9 is split into two parts, a-b. Moreover, OP4 mostly equals OP1 (thus, we speak of 14 trajectories in our paper). For completeness, however, we provide all recorded trajectories here. </p>
NPM3D dataset with instance label. Dataset used in paper "A Review of Panoptic Segmentation for Mobile Mapping Point Clouds"
<p>NPM3D is a public benchmark for point cloud semantic segmentation, with 10 classes including: ground, building, pole (road sign and traffic light), bollard, trash can, barrier, pedestrian, car, natural (vegetation) and unclassified. Results are evaluated only w.r.t. 9 classes, disregarding the "unclassified" label. The data has been captured with a mapping-grade mobile laser scanning system in different cities in France. There are 4 regions designated for training, all captured in Paris and Lille; and 3 regions for testing, captured in Dijon and Ajaccio. The standard 10-class version described above has actually been derived from a more fine-grained version of the dataset by keeping only the most frequent labels. The original annotations feature 50 different semantic classes (most of which are very rare), and also individual object instance labels for the training regions. For panoptic segmentation, a new version has been generated that still uses the 10 semantic category labels listed above, but also includes instance labels. The classes ground, building and barrier are considered "stuff" and are not separated into instances. As no instance labels are available for the 3 test regions, our version for panoptic (or pure instance) segmentation only contains 4 different regions from Paris and Lille. Instead of a fixed training/test split all experiments therefore use 4-fold cross-validation.</p>
Mapping scrub vegetation cover from photogrammetric point-clouds
<p>This dataset is derived from photogrammetric point cloud models of UAV imagery. It includes the Above ground models of vegetation as well as the isolated scrub vegetation.</p> <p>We illustrate the method with two case studies from the UK. The scrub cover at Daneway Banks, a calcareous grassland site in Gloucestershire was calculated at 21.8% of the site. The scrub cover at Flat Holm Island, a maritime grassland in the Severn Estuary was calculated at 7%. This approach enabled the scrub layer to be readily measured and if required, modelled to provide a visual guide of what a projected management objective would look like. This approach provides a new tool in reserve management, enabling habitat management strategies to be informed, and progress towards objectives monitored.</p>
Mapping scrub vegetation cover from photogrammetric point-clouds
Open the record for dataset details and reuse information.
A Dynamic Points Removal Benchmark in Point Cloud Maps
<p>Uniformat Dataset LiDAR Point Cloud Data [PCD format: with pose and points (x,y,z,/i)] <br>We recommend you read this wiki page first to know about data: <a href="https://kth-rpl.github.io/DynamicMap_Benchmark/data/">https://kth-rpl.github.io/DynamicMap_Benchmark/data/</a><br>For methods detail: <a href="https://github.com/KTH-RPL/DynamicMap_Benchmark">DynamicMap_Benchmark repo</a>, <a href="https://github.com/KTH-RPL/dufomap">DUFOMap</a>, <a href="https://github.com/MKJia/BeautyMap">BeautyMap</a>.</p> <ul> <li>00: <a href="https://www.cvlibs.net/datasets/kitti/index.php">KITTI sequence</a> 00 [VLP-64] from frame 4390 to 4530</li> <li>05: <a href="https://www.cvlibs.net/datasets/kitti/index.php">KITTI sequence</a> 05 [VLP-64] from frame 2350 to 2670</li> <li>av2: <a href="https://www.argoverse.org/av2.html">Argoverse 2.0</a> one sequence on <em>07YOTznatmYypvQYpzviEcU3yGPsyaGg__Spring_2020. </em>[2 x VLP-32]</li> <li>KTH campus: <a href="https://mcdviral.github.io/">CVPR'24 MCD</a>(Leica RTC360) For convenience teaser running, we include only 18 frames in data. Please check <a href="https://mcdviral.github.io/">the MCD project page</a> for more.</li> <li>semindoor: semi-indoor dataset collected by [VLP-16], collected by ourselves. </li> <li>twofloor: complex structure with two floors[Livox mid-360], collected by ourselves.</li> </ul> <p> </p> <table> <tbody> <tr> <td>Dataset</td> <td>Description</td> <td>Sensor Type</td> <td>Total Frame Number</td> </tr> <tr> <td>KITTI sequence 00</td> <td>in a small town with few dynamics (including one pedestrian around)</td> <td>VLP-64</td> <td>141</td> </tr> <tr> <td>KITTI sequence 05</td> <td>in a small town straight way, one higher car, the benchmarking paper cover image from this sequence.</td> <td>VLP-64</td> <td>321</td> </tr> <tr> <td>Argoverse2</td> <td>in a big city, crowded and tall buildings (including cyclists, vehicles, people walking near the building etc.</td> <td>2 x VLP-32</td> <td>575</td> </tr> <tr> <td>KTH campus (no gt)</td> <td>Collected by us (Thien-Minh) on the KTH campus. Lots of people move around on the campus. The DUFOMap paper cover image is from this one.</td> <td>Leica RTC360</td> <td>18</td> </tr> <tr> <td>Semi-indoor</td> <td>Collected by us (Qingwen & Mingkai), running on a small 1x2 vehicle with two people walking around the platform.</td> <td>VLP-16</td> <td>960</td> </tr> <tr> <td>Twofloor (no gt)</td> <td>Collected by us (Bowen Yang) in a quadruped robot. A two-floor structure environment with one pedestrian around.</td> <td>Livox-mid 360</td> <td>3305</td> </tr> </tbody> </table> <p> </p> <p>Cite as:</p> <blockquote> <p>@inproceedings{zhang2023benchmark,<br> author={Zhang, Qingwen and Duberg, Daniel and Geng, Ruoyu and Jia, Mingkai and Wang, Lujia and Jensfelt, Patric},<br> booktitle={IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)}, <br> title={A Dynamic Points Removal Benchmark in Point Cloud Maps}, <br> year={2023},<br> pages={608-614},<br> doi={10.1109/ITSC57777.2023.10422094}<br>}<br>@article{jia2024beautymap,<br> author={Jia, Mingkai and Zhang, Qingwen and Yang, Bowen and Wu, Jin and Liu, Ming and Jensfelt, Patric},<br> journal={IEEE Robotics and Automation Letters}, <br> title={{BeautyMap}: Binary-Encoded Adaptable Ground Matrix for Dynamic Points Removal in Global Maps}, <br> year={2024},<br> volume={9},<br> number={7},<br> pages={6256-6263},<br> doi={10.1109/LRA.2024.3402625}<br>}<br>@article{daniel2024dufomap,<br> author={Duberg, Daniel and Zhang, Qingwen and Jia, Mingkai and Jensfelt, Patric},<br> journal={IEEE Robotics and Automation Letters}, <br> title={{DUFOMap}: Efficient Dynamic Awareness Mapping}, <br> year={2024},<br> volume={9},<br> number={6},<br> pages={5038-5045},<br> doi={10.1109/LRA.2024.3387658}<br>}</p> </blockquote> <p> </p> <p>If you use this data, feel free to add your project to <a href="https://kth-rpl.github.io/DynamicMap_Benchmark/papers/">https://kth-rpl.github.io/DynamicMap_Benchmark/papers/</a></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.