Dataset Open Access

Pollen Video Library for Benchmarking Detection, Classification, Tracking and Novelty Detection Tasks

Nam Cao; Matthias Meyer; Lothar Thiele; Olga Saukh


JSON-LD (schema.org) Export

{
  "description": "<p><strong>Dataset description</strong></p>\n\n<p>This dataset contains microscopic images and videos of pollen gathered between Feb. and Aug. 2020 in Graz, Austria.</p>\n\n<ul>\n\t<li>\n\t<p>Pollen images of 16 types:&nbsp;<code>...images_16_types.zip</code></p>\n\n\t<ul>\n\t\t<li>Acer Pseudoplatanus</li>\n\t\t<li>Aesculus Carnea</li>\n\t\t<li>Alnus</li>\n\t\t<li>Anthoxanthum</li>\n\t\t<li>Betula Pendula</li>\n\t\t<li>Brassica</li>\n\t\t<li>Carpinus</li>\n\t\t<li>Corylus</li>\n\t\t<li>Dactylis Glomerata</li>\n\t\t<li>Fraxinus</li>\n\t\t<li>Pinus Nigra</li>\n\t\t<li>Platanus</li>\n\t\t<li>Populus Nigra</li>\n\t\t<li>Prunus Avium</li>\n\t\t<li>Sequoiadendron Giganteum</li>\n\t\t<li>Taxus Baccata</li>\n\t</ul>\n\t</li>\n\t<li>\n\t<p>Pollen video library&nbsp;<code>...pollen_video_library.zip</code></p>\n\n\t<ul>\n\t\t<li>Each type of pollen is in a separate folder, there may be multiple videos per type.</li>\n\t\t<li>In each pollen folder, we included images cropped from the videos by YOLO object detection algorithm trained on a subset of pollen images as described in [1].</li>\n\t\t<li>Cropped file name structure&nbsp;<code>[Video file name]_[TrackingID]_[Image index of a grain]_[Frame index in video]</code>\n\t\t<ul>\n\t\t\t<li>Example, if a grain has 5 images, the file name would be:\n\t\t\t<pre><code> Anthoxanthum-grass-20200530-122652_0000000_001_00001.jpg\n Anthoxanthum-grass-20200530-122652_0000000_002_00002.jpg\n ...\n Anthoxanthum-grass-20200530-122652_0000000_005_00005.jpg\n</code></pre>\n\t\t\t</li>\n\t\t</ul>\n\t\t</li>\n\t</ul>\n\t</li>\n\t<li>\n\t<p>Field data over 3 days are gathered in Graz in spring 2020.&nbsp;<code>...pollen_field_data.zip</code></p>\n\t</li>\n\t<li>\n\t<p>Sample code to load the data and visualize the images is in&nbsp;<code>...plot_pollen_sample.py</code>. Download and extract the file&nbsp;<code>...images_16_types.zip</code>&nbsp;in the same folder as&nbsp;<code>...plot_pollen_sample.py</code>&nbsp;to run the example.</p>\n\t</li>\n</ul>\n\n<p><strong>Dependecies:</strong></p>\n\n<ul>\n\t<li>opencv</li>\n\t<li>numpy</li>\n\t<li>matplotlib</li>\n</ul>\n\n<p><strong>Credit</strong></p>\n\n<p>[1] N. Cao, M. Meyer, L. Thiele, and O. Saukh. 2020. Automated Pollen Detection with an Affordable Technology. In Proceedings of the International Conference on Embedded Wireless Systems and Networks (EWSN). 108&ndash;119.</p>\n\n<pre><code>@inproceedings{namcao2020pollen,\n  title = {Automated Pollen Detection with an Affordable Technology},\n  author = {Nam Cao and Matthias Meyer and Lothar Thiele and Olga Saukh},\n  booktitle = {Proceedings of the International Conference on Embedded Wireless Systems and Networks (EWSN)},\n  pages={108\u2013119}\n  month = {2},\t\n  year = {2020},\n}</code></pre>", 
  "license": "https://creativecommons.org/licenses/by/4.0/legalcode", 
  "creator": [
    {
      "affiliation": "Institute of Technical Informatics, Graz University of Technology, Austria", 
      "@id": "https://orcid.org/0000-0003-2058-1335", 
      "@type": "Person", 
      "name": "Nam Cao"
    }, 
    {
      "affiliation": "Computer Engineering and Networks Lab, ETH Zurich", 
      "@id": "https://orcid.org/0000-0001-6895-2823", 
      "@type": "Person", 
      "name": "Matthias Meyer"
    }, 
    {
      "affiliation": "Computer Engineering and Networks Lab, ETH Zurich", 
      "@type": "Person", 
      "name": "Lothar Thiele"
    }, 
    {
      "affiliation": "Institute of Technical Informatics, Graz University of Technology, Austria, Complexity Science Hub Vienna, Austria", 
      "@id": "https://orcid.org/0000-0001-7849-3368", 
      "@type": "Person", 
      "name": "Olga Saukh"
    }
  ], 
  "url": "https://zenodo.org/record/4120033", 
  "datePublished": "2020-10-23", 
  "@context": "https://schema.org/", 
  "distribution": [
    {
      "contentUrl": "https://zenodo.org/api/files/c407dcf1-61cb-4aed-bfe3-67042f9b830a/Nam_Cao-Dataset_Pollen_Video_Library_for_Benchmarking_Detection_Classification_Tracking_and_Novelty_Detection_Tasks-images_16_types.zip", 
      "encodingFormat": "zip", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/c407dcf1-61cb-4aed-bfe3-67042f9b830a/Nam_Cao-Dataset_Pollen_Video_Library_for_Benchmarking_Detection_Classification_Tracking_and_Novelty_Detection_Tasks-plot_pollen_sample.py", 
      "encodingFormat": "py", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/c407dcf1-61cb-4aed-bfe3-67042f9b830a/Nam_Cao-Dataset_Pollen_Video_Library_for_Benchmarking_Detection_Classification_Tracking_and_Novelty_Detection_Tasks-pollen_field_data.zip", 
      "encodingFormat": "zip", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/c407dcf1-61cb-4aed-bfe3-67042f9b830a/Nam_Cao-Dataset_Pollen_Video_Library_for_Benchmarking_Detection_Classification_Tracking_and_Novelty_Detection_Tasks-pollen_video_library.zip", 
      "encodingFormat": "zip", 
      "@type": "DataDownload"
    }
  ], 
  "identifier": "https://doi.org/10.5281/zenodo.4120033", 
  "@id": "https://doi.org/10.5281/zenodo.4120033", 
  "@type": "Dataset", 
  "name": "Pollen Video Library for Benchmarking Detection, Classification, Tracking and Novelty Detection Tasks"
}
91
88
views
downloads
All versions This version
Views 9191
Downloads 8888
Data volume 622.6 GB622.6 GB
Unique views 7171
Unique downloads 3131

Share

Cite as