February 12, 2020 Dataset Open Access

Ceolini, Enea; Taverni, Gemma; Payvand, Melika; Donati, Elisa

JSON-LD (schema.org) Export

{
  "description": "<p>This dataset contains data for hand gesture recognition recorded with 3 different sensors.&nbsp;</p>\n\n<p>sEMG: recorded via the Myo armband that is composed of 8 equally spaced non-invasive sEMG sensors that can be placed approximately around the middle of the forearm. The sampling frequency of Myo is 200 Hz. The output of the Myo is a.u&nbsp;</p>\n\n<p>DVS: Dynamic Video Sensor which is a very low power event-based camera with 128x128 resolution</p>\n\n<p>DAVIS: Dynamic Video Sensor which is a very low power event-based camera with 240x180 resolution that also acquires APS frames.</p>\n\n<p>The dataset contains recordings of 21 subjects. Each subject performed 3 sessions, where each of the 5 hand gesture was recorded 5 times, each lasting for 2s. Between the gestures a relaxing phase of 1s is present where the muscles could go to the rest position, removing any residual muscular activation.</p>\n\n<p>&nbsp;</p>\n\n<p>Note: All the information for the DVS sensor has been extracted and can be found in the *.npy files. In case the raw data (.aedat) was needed please contact</p>\n\n<p>&nbsp;</p>\n\n<p>enea.ceolini@ini.uzh.ch</p>\n\n<p>elisa@ini.uzh.ch</p>\n\n<p>==== README ====</p>\n\n<p>&nbsp;</p>\n\n<p>DATASET STRUCTURE:</p>\n\n<p>EMG, DVS and APS recordings</p>\n\n<p>21 subjects</p>\n\n<p>3 sessions for each subject</p>\n\n<p>5 gestures in each session (&#39;pinky&#39;, &#39;elle&#39;, &#39;yo&#39;, &#39;index&#39;, &#39;thumb&#39;)</p>\n\n<p>&nbsp;</p>\n\n<p>SINGLE DATASETS:</p>\n\n<p>- relax21_raw_emg.zip: contains raw sEMG and annotations (ground truth of gestures) in the format `subjectXX_sessionYY_ZZZ` with `XX` subject ID (01 to 21), `YY` session ID (01-03) and `ZZZ` that can be &lsquo;emg&rsquo; or &lsquo;ann&rsquo;.</p>\n\n<p>&nbsp;</p>\n\n<p>- relax21_raw_dvs.zip: contains the full-frame dvs events in an array with dimensions 0 -&gt; addr_x, 1 -&gt; addr_y, 2 -&gt; timestamp, 3 -&gt; polarity. The timestamps are in seconds and synchronized with the Myo. Each file is in the format `subjectXX_sessionYY_dvs` with `XX` subject ID (01 to 21), `YY` session ID (01-03).</p>\n\n<p>&nbsp;</p>\n\n<p>- relax21_cropped_aps.zip: contains the 40x40 pixel aps frames for all subjects and trials in the format `subjectXX_sessionYY_Z_W_K` with `XX` subject ID (01 to 21), `YY` session ID (01-03), Z gesture (&#39;pinky&#39;, &#39;elle&#39;, &#39;yo&#39;, &#39;index&#39;, &#39;thumb&rsquo;), W trial ID (1-5), `K` frame index.</p>\n\n<p>&nbsp;</p>\n\n<p>- relax21_cropped_dvs_emg_spikes.pkl: spiking dataset that can be used to reproduce the results in the paper. The dataset is a dictionary with the following keys:</p>\n\n<ul>\n\t<li><strong>- </strong><strong>y</strong>: array of size 1xN with the class (0-&gt;4).</li>\n\t<li><strong>- </strong><strong>sub</strong>: array of size 1xN with the subject id (1-&gt;10).</li>\n\t<li><strong>- </strong><strong>sess</strong>: array of size 1xN with the session id (1-&gt;3).</li>\n\t<li><strong>- </strong><strong>dvs</strong>: list of length N, each object in the list is a 2d array of size 4xT_n where T_n is the number of events in the trial and the 4 dimensions rappresent: 0 -&gt; addr_x, 1 -&gt; addr_y, 2 -&gt; timestamp, 3 -&gt; polarity .</li>\n\t<li><strong>- </strong><strong>emg</strong>: list of length N, each object in the list is a 2d array of size 3xT_n where T_n is the number of events in the trial and the 3 dimensions rappresent: 0 -&gt; addr, 1 -&gt; timestamp, 3 -&gt; polarity.</li>\n</ul>\n\n<p>&nbsp;</p>\n\n<p>&nbsp;</p>", 
  "license": "https://creativecommons.org/licenses/by/4.0/legalcode", 
  "creator": [
    {
      "affiliation": "Institute of Neuroinformatics, UZH/ETH Zurich", 
      "@id": "https://orcid.org/0000-0002-2676-0804", 
      "@type": "Person", 
      "name": "Ceolini, Enea"
    }, 
    {
      "affiliation": "Institute of Neuroinformatics, UZH/ETH Zurich", 
      "@id": "https://orcid.org/0000-0001-8951-3133", 
      "@type": "Person", 
      "name": "Taverni, Gemma"
    }, 
    {
      "affiliation": "Institute of Neuroinformatics, UZH/ETH Zurich", 
      "@id": "https://orcid.org/0000-0001-5400-067X", 
      "@type": "Person", 
      "name": "Payvand, Melika"
    }, 
    {
      "affiliation": "Institute of Neuroinformatics, UZH/ETH Zurich", 
      "@id": "https://orcid.org/0000-0002-8091-1298", 
      "@type": "Person", 
      "name": "Donati, Elisa"
    }
  ], 
  "url": "https://zenodo.org/record/3663616", 
  "datePublished": "2020-02-12", 
  "version": "3.0", 
  "keywords": [
    "EMG", 
    "DVS", 
    "DAVIS", 
    "Hand gesture recognition", 
    "Sensor fusion", 
    "Myo"
  ], 
  "@context": "https://schema.org/", 
  "distribution": [
    {
      "contentUrl": "https://zenodo.org/api/files/102a63cc-433e-49b4-be9f-3ee2f482b38e/relax21_cropped_aps.zip", 
      "encodingFormat": "zip", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/102a63cc-433e-49b4-be9f-3ee2f482b38e/relax21_cropped_dvs_emg_spikes.pkl", 
      "encodingFormat": "pkl", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/102a63cc-433e-49b4-be9f-3ee2f482b38e/relax21_raw_dvs.zip", 
      "encodingFormat": "zip", 
      "@type": "DataDownload"
    }, 
    {
      "contentUrl": "https://zenodo.org/api/files/102a63cc-433e-49b4-be9f-3ee2f482b38e/relax21_raw_emg.zip", 
      "encodingFormat": "zip", 
      "@type": "DataDownload"
    }
  ], 
  "identifier": "https://doi.org/10.5281/zenodo.3663616", 
  "@id": "https://doi.org/10.5281/zenodo.3663616", 
  "@type": "Dataset", 
  "name": "EMG and Video Dataset for sensor fusion based hand gestures recognition"
}