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.
86
datasets available to search
ShareScore release 0.9.0
Dataset results
86 results for “RGB images”
VegAnn: Vegetation Annotation of a large multi-crop RGB Dataset acquired under diverse conditions for image segmentation
<p> VegAnn - Vegetation Annotation - dataset, a collection of 3795 multi-crop RGB images acquired for different phenological stages using different systems and platforms in diverse illumination conditions. </p>
WE3DS: An RGB-D image dataset for semantic segmentation in agriculture
<p>Here, we introduce a novel RGB-D image database (WE3DS) for semantic segmentation in crop farming. It contains 2,568 RGB-D images (color image and distance map) and hand-annotated ground-truth masks for semantic segmentation and is the first RGB-D image dataset for multi-class plant species semantic segmentation task. Images were taken under natural light conditions using an RGB-D sensor consisting of two RGB cameras in a stereo setup.</p> <p> </p> <p><strong>Please cite the original source when using this dataset.</strong></p> <p>Kitzler, F.; Barta, N.; Neugschwandtner, R.W.; Gronauer, A.; Motsch, V. WE3DS: An RGB-D Image Dataset for Semantic Segmentation in Agriculture. <em>Sensors</em> <strong>2023</strong>, <em>23</em>, 2713. <a href="https://doi.org/10.3390/s23052713">https://doi.org/10.3390/s23052713 </a></p>
Cape Hatteras Landsat8 RGB Images and Labels for Image Segmentation using the program, Segmentation Zoo
<p># Cape Hatteras Landsat8 RGB Images and Labels for Image Segmentation using the program, Segmentation Gym</p> <p>## Overview<br> * Test datasets and files for testing the [segmentation gym](https://github.com/Doodleverse/segmentation_gym) program for image segmentation<br> * Data set made by Daniel Buscombe, Marda Science LLC. This is version 5.0<br> * Dataset consists of a time-series of Landsat-8 images of Cape Hatteras National Seashore, courtesy of the U.S. Geological Survey.<br> * Imagery spans the period February 2015 to September 2021.<br> * Labels were created by Daniel Buscombe, Marda Science, using the labeling program [Doodler](https://github.com/Doodleverse/dash_doodler).</p> <p>Download this file and unzip to somewhere on your machine (although *not* inside the `segmentation_gym` folder), then see the relevant page on the [segmentation gym wiki](https://github.com/Doodleverse/segmentation_gym/wiki) for further explanation.</p> <p>This dataset and associated models were made by Dr Daniel Buscombe, Marda Science LLC, for the purposes of demonstrating the functionality of Segmentation Gym. The labels were created using [Doodler](https://github.com/Doodleverse/dash_doodler/).</p> <p>Previous versions:</p> <p>1.0. https://zenodo.org/record/5895128#.Y1G5s3bMIuU original release, Oct 2021, conforming to Segmentation Gym functionality on Oct 2021</p> <p>2.0 https://zenodo.org/record/7036025#.Y1G57XbMIuU, Jan 23 2022, conforming to Segmentation Gym functionality on Jan 23 2022</p> <p>This is version 5.0, created 7/20/23, and has been tested with Segmentation Gym using doodleverse-utils 0.0.33 https://pypi.org/project/doodleverse-utils/0.0.33/</p> <p> </p> <p>## file structure</p> <p>```{sh}<br> /Users/Someone/my_segmentation_zoo_datasets<br> │ ├── config<br> │ | └── *.json<br> │ ├── capehatteras_data<br> | | ├── fromDoodler<br> | | | ├──images<br> │ | | └──labels<br> | | ├──npzForModel<br> │ | └──toPredict<br> │ └── modelOut<br> │ └── *.png<br> │ └── weights<br> │ └── *.h5</p> <p>```</p> <p>## config<br> There are 4 config files:<br> 1. `/config/hatteras_l8_resunet.json`<br> 2. `/config/hatteras_l8_vanilla_unet.json`<br> 3. `/config/hatteras_l8_resunet_model2.json`</p> <p>4. `/config/hatteras_l8_segformer.json`<br> </p> <p> </p> <p>The first two are for res-unet and unet models respectively. The third one differs from the first only with specification of kernel size. It is provided as an example of how to conduct model training experiments, modifying one hyperparameter at a time in the effort to create an optimal model. The last one is based on the new Segformer model architecture.</p> <p>They all contain the same essential information and differ as indicated below</p> <p>```<br> {<br> "TARGET_SIZE": [768,768], # the size of the imagery you wish the model to train on. This may not be the original size<br> "MODEL": "resunet", # model name. Otherwise, "unet" or "segformer"<br> "NCLASSES": 4, # number of classes<br> "KERNEL":9, # horizontal size of convolution kernel in pixels<br> "STRIDE":2, # stride in convolution kernel<br> "BATCH_SIZE": 7, # number of images/labels per batch<br> "FILTERS":6, # number of filters<br> "N_DATA_BANDS": 3, # number of image bands<br> "DROPOUT":0.1, # amount of dropout<br> "DROPOUT_CHANGE_PER_LAYER":0.0, # change in dropout per layer<br> "DROPOUT_TYPE":"standard", # type of dropout. Otherwise "spatial"<br> "USE_DROPOUT_ON_UPSAMPLING":false, # if true, dropout is used on upsampling as well as downsampling<br> "DO_TRAIN": false, # if false, the model will not train, but you will select this config file, data directory, and the program will load the model weights and test the model on the validation subset<br> if true, the model will train from scratch (warning! this will overwrite the existing weights file in h5 format)<br> "LOSS":"dice", # model training loss function, otherwise "cat" for categorical cross-entropy<br> "PATIENCE": 10, # number of epochs of no model improvement before training is aborted<br> "MAX_EPOCHS": 100, # maximum number of training epochs<br> "VALIDATION_SPLIT": 0.6, #proportion to use for validation<br> "RAMPUP_EPOCHS": 20, # [LR-scheduler] rampup to maximim<br> "SUSTAIN_EPOCHS": 0.0, # [LR-scheduler] sustain at maximum<br> "EXP_DECAY": 0.9, # [LR-scheduler] decay rate<br> "START_LR": 1e-7, # [LR-scheduler] start lr<br> "MIN_LR": 1e-7, # [LR-scheduler] min lr<br> "MAX_LR": 1e-4, # [LR-scheduler] max lr<br> "FILTER_VALUE": 0, #if >0, the size of a median filter to apply on outputs (not recommended unless you have noisy outputs)<br> "DOPLOT": true, #make plots<br> "ROOT_STRING": "hatteras_l8_aug_768", #data file (npz) prefix string<br> "USEMASK": false, # use the convention 'mask' in label image file names, instead of the preferred 'label'<br> "AUG_ROT": 5, # [augmentation] amount of rotation in degrees<br> "AUG_ZOOM": 0.05, # [augmentation] amount of zoom as a proportion<br> "AUG_WIDTHSHIFT": 0.05, # [augmentation] amount of random width shift as a proportion<br> "AUG_HEIGHTSHIFT": 0.05,# [augmentation] amount of random width shift as a proportion<br> "AUG_HFLIP": true, # [augmentation] if true, randomly apply horizontal flips<br> "AUG_VFLIP": false, # [augmentation] if true, randomly apply vertical flips<br> "AUG_LOOPS": 10, #[augmentation] number of portions to split the data into (recommended > 2 to save memory)<br> "AUG_COPIES": 5 #[augmentation] number iof augmented copies to make<br> "SET_GPU": "0" #which GPU to use. If multiple, list separated by a comma, e.g. '0,1,2'. If CPU is requested, use "-1"<br> "WRITE_MODELMETADATA": false, #if true, the prompts `seg_images_in_folder.py` to write detailed metadata for each sample file<br> "LOSS_WEIGHTS": false, #if true, apply per-class weights to loss function</p> <p> "SET_PCI_BUS_ID": true, #if true, make keras aware of the PCI BUS ID (advanced or nonstandard GPU usage)</p> <p> "TESTTIMEAUG": true, #if true, apply test-time augmentation when model in inference mode</p> <p> "WRITE_MODELMETADATA": true,# if true, write model metadata per image when model in inference mode</p> <p> "OTSU_THRESHOLD": true# if true, and NCLASSES=2 only, use per-image Otsu threshold rather than decision boundary of 0.5 on softmax scores</p> <p>}<br> ```</p> <p>## capehatteras_data<br> Folder containing all the model input data</p> <p>```{sh}<br> │ ├── capehatteras_data: folder containing all the model input data<br> | | ├── fromDoodler: folder containing images and labels exported from Doodler using [this program](https://github.com/dbuscombe-usgs/dash_doodler/blob/main/utils/gen_images_and_labels_4_zoo.py)<br> | | | ├──images: jpg format files, one per label image<br> │ | | └──labels: jpg format files, one per image<br> | | ├──npz4gym npz format files for model training using [this program](https://github.com/dbuscombe-usgs/segmentation_zoo/blob/main/train_model.py) that have been created following the workflow [documented here](https://github.com/dbuscombe-usgs/segmentation_zoo/wiki/Create-a-model-ready-dataset) using [this program](https://github.com/dbuscombe-usgs/segmentation_zoo/blob/main/make_nd_dataset.py)<br> │ | └──toPredict: a folder of images to test model prediction using [this program](https://github.com/dbuscombe-usgs/segmentation_zoo/blob/main/seg_images_in_folder.py)<br> ```</p> <p>## modelOut<br> PNG format files containing example model outputs from the train ('_train_' in filename) and validation ('_val_' in filename) subsets as well as an image showing training loss and accuracy curves with `trainhist` in the filename. There are two sets of these files, those associated with the residual unet trained with dice loss contain `resunet` in their name, and those from the UNet are named with `vanilla_unet`.</p> <p>## weights<br> There are model weights files associated with each config files.</p>
SiEUGreen - Data for 'Deep Learning in Hyperspectral Image Reconstruction from Single RGB images—A Case Study on Tomato Quality Parameters'
<p>Dataset used in the scientific publication <a href="https://zenodo.org/record/4671852">'Deep Learning in Hyperspectral Image Reconstruction from Single RGB images—A Case Study on Tomato Quality Parameters'</a>. The data includes chemical contents of tomatoes that was measured, images and scripts used in the paper. The scripts here aim to predict tomato quality parameters, sugar content, acidity, sugar acid ratio and lycopene, of automatically segmented tomato through hyperspectral image reconstruction from single RGB image. The same data can also be found at the <a href="https://github.com/ZJiangsan/TomatoQualityPredictionOnAutomaticallySegmentedTomato">Github repository</a>. The data collection and scientific paper was produced by SiEUGreen partners at Norwegian Institute of Bioeconomy Research (NIBIO).</p>
A dataset of 1600 images extracted from 5 cm RGB orthophotos for the classification of 12 classes of roofing materials
<p>This dataset contains a collection of 1601 image tiles of 64x64 pixels (3.2x3.2m²) annotated for 12 roofing materials. These tiles were extracted from 5 cm RGB orthophotos acquired by the city of Namur (Belgium) in 2017. The additional data used to create this dataset are (a) a Namur roof section mask, and (b) a set of 1601 material samples acquired using stratified random sampling. The tiles were obtained as follows: the centroid of each roof section containing a sample is used to extract tiles. A size of 64x64 pixels has been chosen so that a tile contains information for only one roof section, in order to learn only the colour and texture of the roof materials. This also avoids adding information outside the given roof section. The tiles are thus extracted for each orthophoto spectral band and labelled with the identifier of the class of roofing materials to which they belong. Here are the 12 material classes considered, preceded by their labels:</p> <p>0- Solar panels<br>1- Brown tiles<br>2- Orange tiles<br>3- Black tiles<br>4- Dark membranes<br>5- White membranes<br>6- Slates containing asbestos<br>7- Slates without asbestos<br>8- Corrugated asbestos-cement sheets<br>9- Gravel<br>10- Vegetation<br>12- Metals</p> <p>There are approximately 140 tiles by material class except for the vegetated roof sections (class 10) which contains only 47 samples due to its rarety.</p> <p>The dataset contains 1 folder for each spectral band. Each folder contains 1601 thumbnails in tif format named as follows:</p> <p><strong>img[tile id]_[class label].tif</strong></p> <p>It is suggested to apply pre-processing to these images as done by<a href="https://doi.org/10.1109/jurse57346.2023.10144142"> Wyard et al. (2023).</a></p>
RGB and Thermal Integral Image dataset for Search and Rescue with Airborne Optical Sectioning.
<p>The `Integral Images` folder contains labels and augmented AOS integral images (both RGB and Thermal) used for training, validation and testing (`data`).</p> <p>The integral images are computed using the complete data that were recorded during 18 flights at 6 different sites over 10 different days.</p> <p> </p> <p>The dataset mirrors [YOLO (8GB)](https://zenodo.org/record/3894774/files/YOLO.zip?download=1) (`data`) for integral (`SARAOS/AOS`) images, however, now additionally contain corresponding RGB integral images in addition to corresponding thermal integral images.</p>
Dataset for detecting the electrical behavior of photovoltaic panels from RGB images
<p>The dynamic reconfiguration and maximum power point tracking in large-scale photovoltaic (PV) systems require a large number of voltage and current sensors. In particular, the reconfiguration process requires a pair of voltage/current sensors for each panel, which introduces costs, increases size and reduces reliability of the installation. A suitable solutions for reducing the number of sensors is to adopt image-based solution to estimate the electrical characteristics of the PV panels, but the lack of reliable data with large diversity of irradiance and shading conditions is a major problem in this topic. Therefore, this paper presents dataset correlating RGB images and electrical data of PV panels with different irradiance and shading conditions. The dataset was designed to support the design of image-based estimators of electrical data, which could be used to replace large arrays of sensors. The paper also describes the measurement platform used to collect the data, which helps to replicate the experiments in different geographical locations.</p>
Doodleverse/Segmentation Zoo Res-UNet models for identifying water in Sentinel-2 and Landsat RGB images of coasts. CoastTrain-only version
<p><strong>Doodleverse/Segmentation Zoo Res-UNet models for identifying water in Sentinel-2 and Landsat RGB images of coasts.</strong></p> <p><strong>Based on Coast Train*** data</strong></p> <p>These Residual-UNet model data are based on images of coasts and associated labels. Models have been fitted to the following types of data</p> <p>1. RGB (3 band): red, green, blue</p> <p>Classes are: {0: null, 1: water}.</p> <p>These files are used in conjunction with Segmentation Zoo*</p> <p>For each model, there are 3 files with the same root name:</p> <p>1. <strong>'.json' </strong>config file: this is the file that was used by Segmentation Gym** to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.</p> <p> </p> <p>2.<strong> '.h5'</strong> weights file: this is the file that was created by the Segmentation Gym** function `train_model.py`. It contains the trained model's parameter weights. It can called by the Segmentation Gym** function `seg_images_in_folder.py` or the Segmentation Zoo* function `select_model_and_batch_process_folder.py` to segment a folder of images</p> <p> </p> <p>3.<strong> '_modelcard.json'</strong> model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the `config` file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model</p> <p>4. <strong>'_history.npz'</strong> files contain model training metrics</p> <p> </p> <p>One additional file, BEST_MODEL.txt, contains the name of the model with the highest validation accuracy</p> <p> </p> <p>References</p> <p>* https://github.com/Doodleverse/segmentation_zoo</p> <p>** https://github.com/Doodleverse/segmentation_gym</p> <p>*** https://dbuscombe-usgs.github.io/CoastTrain/docs/Version%201:%20March%202022/data</p>
Doodleverse/Segmentation Zoo Res-UNet models for identifying water in Sentinel-2 RGB images of coasts. SWED-only version
<p><strong>Doodleverse/Segmentation Zoo Res-UNet models for identifying water in Sentinel-2 RGB images of coasts.</strong></p> <p><strong>Based on SWED*** data</strong></p> <p>https://openmldata.ukho.gov.uk/</p> <p>These Residual-UNet model data are based on images of coasts and associated labels. Models have been fitted to the following types of data</p> <p>1. RGB (3 band): red, green, blue</p> <p>Classes are: {0: null, 1: water}.</p> <p>These files are used in conjunction with Segmentation Zoo*</p> <p>For each model, there are 3 files with the same root name:</p> <p>1. <strong>'.json' </strong>config file: this is the file that was used by Segmentation Gym** to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.</p> <p> </p> <p>2.<strong> '.h5'</strong> weights file: this is the file that was created by the Segmentation Gym** function `train_model.py`. It contains the trained model's parameter weights. It can called by the Segmentation Gym** function `seg_images_in_folder.py` or the Segmentation Zoo* function `select_model_and_batch_process_folder.py` to segment a folder of images</p> <p> </p> <p>3.<strong> '_modelcard.json'</strong> model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the `config` file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model</p> <p>4. <strong>'_history.npz'</strong> files contain model training metrics</p> <p> </p> <p>One additional file, BEST_MODEL.txt, contains the name of the model with the highest validation accuracy</p> <p> </p> <p>References</p> <p>* https://github.com/Doodleverse/segmentation_zoo</p> <p>** https://github.com/Doodleverse/segmentation_gym</p> <p>*** https://www.sciencedirect.com/science/article/abs/pii/S0034425722001584</p>
SD4EO: AI-based synthetic satellite Sentinel-2 images of cities and building coverture (RGB+NIR bands)
<p>This dataset has been created as part of the deliverables for ESA’s <a href="https://eo4society.esa.int/projects/sd4eo/">SD4EO project</a>. It consists of synthetic versions of Sentinel-2 images in urban areas. These images were synthetically generated using schematic representations from Open Street Maps as a guide to create AI-based conditioned diffusion model images in the visible and near-infrared spectrum, along with coverage masks for non-residential buildings and the set of residential buildings combined with the former.</p> <p>At least five synthetic variants were generated for each of the eleven cities:</p> <ul> <li>Paris (11 variants)</li> <li>Toulouse (9 variants)</li> <li>Poitiers (8 variants)</li> <li>Bordeaux (6 variants)</li> <li>Limoges (9 variants)</li> <li>Clermont-Ferrand (5 variants)</li> <li>Troyes (6 variants)</li> <li>Le Mans (14 variants)</li> <li>Angers (7 variants)</li> <li>Madrid (15 variants)</li> <li>Niort (6 variants)</li> </ul> <p>The file names within the ZIP archives follow a very simple schema:</p> <p>`assembled_` + city name + usage or band indicator + variant + PNG extension / NC extension</p> <p>Each of the four types of images has a different indicator or band:</p> <ul> <li>`_RGB_` for images encoding visible spectrum signals</li> <li>`_NIR_` for images generated for the near-infrared band</li> <li>`_full_allbuildingmask` for the coverage pixel mask of all building types in floating point</li> <li>`_full_nonresidentialmask` for the coverage pixel mask of non-residential buildings in floating point</li> <li>if we have no indicator, then it is a netCDF file with a labelled xarray that merges RGB+NIR as the original Sentinel-2 spectral bands in full original range</li> </ul> <p>NOTE: This 5th version corrects a minor bug in 3rd version of this dataset. If you want to access to version 4 (with non-already assembled patches), it is also available in the right side control version list.</p> <p>The SD4EO Project is funded by the ESA’s FutureEO programme under contract no. 4000142334/23/I-DT and supervised by ESA Φ-lab.</p>
Doodleverse/Segmentation Zoo Res-UNet models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 7-band (RGB+NIR+SWIR+NDWI+MNDWI) images of coasts.
<p>Doodleverse/Segmentation Zoo Res-UNet models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 7-band (RGB+NIR+SWIR+NDWI+MNDWI) images of coasts.</p> <p>Models have been created using Segmentation Gym* using the following dataset**: https://doi.org/10.5281/zenodo.7344571</p> <p>Classes: {0=water, 1=whitewater, 2=sediment, 3=other}</p> <p>File descriptions</p> <p>For each model, there are 5 files with the same root name:</p> <p>1. '.json' config file: this is the file that was used by Segmentation Gym* to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.</p> <p>2. '.h5' weights file: this is the file that was created by the Segmentation Gym* function `train_model.py`. It contains the trained model's parameter weights. It can called by the Segmentation Gym* function `seg_images_in_folder.py`. Models may be ensembled.</p> <p>3. '_modelcard.json' model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the `config` file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model</p> <p>4. '_model_history.npz' model training history file: this numpy archive file contains numpy arrays describing the training and validation losses and metrics. It is created by the Segmentation Gym function `train_model.py`</p> <p>5. '.png' model training loss and mean IoU plot: this png file contains plots of training and validation losses and mean IoU scores during model training. A subset of data inside the .npz file. It is created by the Segmentation Gym function `train_model.py`</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p><br> References</p> <p>*Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. https://doi.org/10.1029/2022EA002332 See: https://github.com/Doodleverse/segmentation_gym</p> <p>** Buscombe, Daniel. (2022). Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, whitewater, sediment, other) (v1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7344571</p> <p> </p>
RGB and HSL pixel-mean colors of ant specimen head images from AntWeb.org
<p>Our dataset consists of color data extracted from ~50,000 images of ant heads acquired from the database <a href="https://AntWeb.org">AntWeb.org</a>. The .csv file contains the pixel-mean RGB and HSL values of image segments extracted from the ant head images, in addition to the existing metadata for these 50,000 specimens.</p>
RGB and HSL pixel-mean colors of ant specimen head images from AntWeb.org
Open the record for dataset details and reuse information.
RGB and VIS/NIR Hyperspectral Imaging Data for 90 Rice Seed Varieties
<p>The dataset contains 90 rice seed species and 96 kernels per species resulting in 8,640 rice seed kernels in total. The dataset was collected in 2017 using the following two imaging systems:</p> <ol> <li>Visible - Near Infrared (VIS/NIR) Hyperspectral Imaging Device System (~385nm - ~1000nm) consisting of a Specim V10E Imaging Spectrograph and Hamamatsu ORCA-05G CCD camera.</li> <li>RGB - Fujifilm X-M1 with a 35mm/F2.0, ISO 400.</li> </ol> <p>For each species, 96 kernels have been captured in two imaging bundles with 48 kernels in each bundle. For each imaging bundle, the 48 kernels were carefully positioned on a sheet of white paper and arranged in an <code>8x6</code> matrix. This rice seed matrix was then positioned on a translational stage and imaged using the HSI and RGB cameras described above.</p> <p>The following three files result from a single acquisition:</p> <ul> <li><code>.hdr</code>: The HSI ENVI header file (More information on the ENVI format can be found at the <a href="https://www.harrisgeospatial.com/docs/ENVIHeaderFiles.html">Harris Geospatial Solutions</a> documentation.</li> <li><code>.raw</code>: The HSI datacube data.</li> <li><code>.jpg</code>: The RGB image.</li> </ul> <p>The filename convention used is the (short) species name followed by a dash, followed by the bundle number (i.e. 1 or 2), followed by the filename suffix. For instance, the data for the <code>BC15</code> rice seed variety are contained in the following 6 files:</p> <ul> <li><code>BC15-01.hdr</code></li> <li><code>BC15-01.raw</code></li> <li><code>BC15-01.jpg</code></li> <li><code>BC15-02.hdr</code></li> <li><code>BC15-02.raw</code></li> <li><code>BC15-02.jpg</code></li> </ul> <p>The data were captured in 9 batches across multiple days. All the data from the same batch are contained in a dedicated folder. For instance the folder <code>Data-VIS-20170111-2-room-light-off</code>indicates that the data are in the VIS/NIR range, captured on the 11th of January 2017 and this was the second batch for that day with the room lights off. Two halogen bulbs were used for illumination and these were accurately positioned to provide balanced lighting across the scene. To ensure stability, the halogen bulbs were switched on and allowed to reach constant operating temperature before the data were acquired in a dark room to minimise any other sources of illumination variance.</p> <p>For the purposes of calibration each HSI image contains in the scene a 100% reflective spectralon tile which is a highly reflective Lambertian scatter. For the dark reference, each folder contains an HSI image with the lens-cap covering the camera. The dark reference can be founds in each folder under the filename <code>black.hdr</code>/<code>black.raw</code>.</p> <p>A full index of the data for each species is provided in the <code>index.csv</code> file. The file contains the following columns:</p> <ul> <li>Species Full Name: The full species name (as used in filenames).</li> <li>Species Short Name: A shorthand of the species name.</li> <li>Bundle Number: Imaging Bundle Number (each bundle contains 48 kernels) every species has 2 bundles.</li> <li>Folder: The name of the folder containing the data (as described above where each folder contains a batch of images captured in a single imaging session).</li> <li>File Name: The stem of the filename. Note: that there are 3 suffixes for each stem (<code>.hdr</code>, <code>.raw</code>, <code>.jpg</code>)</li> </ul> <p>The HSI system was used to capture 256 wavelengths in this experiment and the exact wavelengths corresponding to the data provided are included in the file <code>wavelengths.csv</code>.</p> <p>Both camera systems were fixed on a rigid frame for the duration of the experiments. To permit possible registration between the two cameras, a chessboard pattern has been imaged and the acquired files are also contained in the folder <code>chessboard</code>.</p> <p><strong>Note:</strong> The bundle <code>01</code> for the species <code>NDC1</code> was originally acquired during the batch <code>Data-VIS-20170111-2-room-light-off</code>. However, the file was corrupted and hence, the acquisition was repeated during the batch <code>Data-VIS-20170203-1-room-light-off</code>. As a result, the <code>NDC1-01</code> files are in the <code>Data-VIS-20170203-1-room-light-off</code> folder.</p>
Data from: LiDAR and RGB-image analysis to predict hairy vetch biomass in breeding nurseries
Hairy vetch is a fall seeded annual legume that can be used as a forage and cover crop. As a cover crop, it can provide numerous ecosystem services, such as soil erosion reduction, carbon sequestration, and pollinator habitat, but also agronomic services such as weed suppression and N fixation via soil rhizobium species. To improve cover crop function, traits such as biomass production are especially relevant, making it a first priority trait for cover crop breeders. However, direct phenotypic methods for biomass production are destructive. Breeders have thus relied on subjective, visual scoring methods for biomass, which are generally correlative, but are not quantitative or absolute. In this study, we evaluated two low-cost remote sensing tools, LiDAR and RGB-image analysis, for their effectiveness at predicting biomass in vivo. We evaluated these tools in two common forage breeding scenarios, spaced-plant and sward-plot nurseries, at three Minnesota locations following the winter of 2016/2017. Ground cover, determined from RGB image binarization using the Canopeo application, had a significant and linear relationship with above-ground biomass in spaced-plants (R2=0.93), and sward-plots (R2=0.89). Once the image area became saturated with vegetative pixels, a near-exponential relationship with biomass would occur. Because of the low-growth habit of hairy vetch, RGB image analysis was more appropriate at lower plant densities, such as spaced-plant nurseries. LiDAR measures of sward-plot height were also linearly and strongly related to dry-matter biomass in sward-plots (R2=0.80). The dimensionality of LiDAR sensing gave it greater predictive ability at higher plant densities, where RGB analysis could not detect vertical increases in biomass production. Lastly, we combined RGB and LiDAR data to predict sward-plot biomass in a multiple mixed-effect regression model. By doing so, we were able to explain more biomass variation than with use of either phenotypic tool as a single predictor (R2=0.94).
Unwarped images in RGB channels
<p>Unwarped images using a height of 425 km and zenith angles less than 80° showing the evolution of the color properties of the arc observed on 17 March 2015 at Dunedin, New Zealand.</p>
Dataset with square plots across Sierra Nevada (Spain) where the contours of all juniper shrubs were annotated as polygons using centimetric GPS and very high resolution aerial and satellite RGB images
<p><strong>This dataset is a shapefile of 767 polygons describing the contours of Juniperus communis L. and Juniperus sabina L. shrubs for the year 2021 in rectangular plots across Sierra Nevada. The coordinates of the polygons were obtained from a field work campaign with a differential centimetric GPS, and their contours were drawn manually in QGIS using the Google Earth satellite image for 2020 and the PNOA aerial image for the 2020. </strong></p> <p><strong>This dataset also contains an excel file describing the features of each polygon: the polygon centroid coordinates, the type of species, the sexgender, the morphotype, the damage in the vegetation cover estimated in the field and telematically, certainty of the digitalization with QGIS and also if the differential centimetric GPS used belongs to the University of Granada or the University of Almeria. </strong></p>
RGB images of PP and PS recyclable waste
<p>A dataset of RGB images depicting multiple PP and PS recyclables on a conveyor belt. The dataset is produced as part of the EU funded project RECLAIM: GA-101070524.</p> <p>Please find the updated version of the PP and PS recyclable waste data at the following link: https://zenodo.org/records/11504659</p>
RGB images of PET recyclable waste
<p>A dataset of RGB images depicting multiple PET recyclables on a conveyor belt. The dataset is produced as part of the EU funded project RECLAIM: GA-101070524.</p> <p>Please find the updated version of PET recyclable waste data at the following link: https://zenodo.org/records/11504415</p>
RGB images of HDPE recyclable waste
<p>A dataset of RGB images depicting multiple HDPE recyclables on a conveyor belt. The dataset is produced as part of the EU funded project RECLAIM: GA-101070524.</p> <p>Please find the updated version of HDPE recyclable waste data at the following link: https://zenodo.org/records/11504453</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.