There is a newer version of this record available.

Dataset Open Access

Mars novelty detection Mastcam labeled dataset

Hannah Kerner; Danika Wellington; Kiri Wagstaff; Jim Bell; Heni Ben Amor

DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="" xmlns="" xsi:schemaLocation="">
  <identifier identifierType="DOI">10.5281/zenodo.1486196</identifier>
      <creatorName>Hannah Kerner</creatorName>
      <affiliation>Arizona State University</affiliation>
      <creatorName>Danika Wellington</creatorName>
      <affiliation>Arizona State University</affiliation>
      <creatorName>Kiri Wagstaff</creatorName>
      <affiliation>Jet Propulsion Laboratory</affiliation>
      <creatorName>Jim Bell</creatorName>
      <affiliation>Arizona State University</affiliation>
      <creatorName>Heni Ben Amor</creatorName>
      <affiliation>Arizona State University</affiliation>
    <title>Mars novelty detection Mastcam labeled dataset</title>
    <subject>Mars, novelty detection, space, multispectral</subject>
    <date dateType="Issued">2018-11-13</date>
  <resourceType resourceTypeGeneral="Dataset"/>
    <alternateIdentifier alternateIdentifierType="url"></alternateIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.1486195</relatedIdentifier>
    <rights rightsURI="">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
    <description descriptionType="Abstract">&lt;p&gt;These datasets were used for experiments in the paper:&lt;br&gt;
Kerner, H. R., Wellington, D. F., Wagstaff, K. L., Bell III, J. F., Ben Amor, H. Novelty Detection for Multispectral Images with Application to Planetary Exploration.&amp;nbsp;In Proceedings of&amp;nbsp;&lt;em&gt;Innovative Applications in Artificial Intelligence (IAAI/AAAI)&lt;/em&gt;, 2019.&amp;nbsp;&lt;/p&gt;

&lt;p&gt;The file contains examples used for training the convolutional autoencoder. Each example is a Numpy array (.npy) of size 64x64x6 pixels.&lt;/p&gt;

&lt;p&gt;The file contains the 332 tiles labeled as &amp;quot;novel&amp;quot; for containing novel geologic features.&amp;nbsp;Each example is a Numpy array (.npy) of size 64x64x6 pixels.&lt;/p&gt;

&lt;p&gt;The file contains examples used for fine-tuning pre-trained networks. Images are divided into &amp;quot;vis&amp;quot; (shorter wavelengths) and &amp;quot;nir&amp;quot; (longer wavelengths) and by their label of &amp;quot;typical&amp;quot; vs. &amp;quot;novel.&amp;quot; These three-channel images are stored as .jpg files.&lt;/p&gt;

&lt;p&gt;All files are named with the following convention: sequence_id_XX*_{R,L}Y_solZZZZ_N.npy where XX* is the sequence ID for the image, {R,L}Y indicates the right (R) or left (L) eye of the camera and the image number in the sequence (Y), and ZZZZ is the four-digit sol (Martian day since the rover began operations) the image was acquired on.&lt;/p&gt;

&lt;p&gt;All source images are publicly released&amp;nbsp;Experiment Data Records (EDRs) archived by&amp;nbsp;the Planetary Data System (PDS).&lt;/p&gt;</description>
All versions This version
Views 553277
Downloads 28798
Data volume 140.2 GB125.1 GB
Unique views 409244
Unique downloads 13947


Cite as