Shadow Detection/Texture Segmentation Computer Vision Dataset

Dataset OPEN
Newey, Charles ; Jones, Owain ; Dee, Hannah
  • Publisher: Zenodo
  • Related identifiers: doi: 10.5281/zenodo.59019
  • Subject: shadow, detection, segmentation, texture, computer, vision

<p>A&nbsp;simple computer vision&nbsp;dataset for shadow detection and texture analysis, specifically created to help test shadow detection algorithms (and texture segmentation algorithms)&nbsp;for mobile robots - that is, shadow detection with an&nbsp;<em>active (moving)&nbsp;camera</em>.</p> <p>The dataset is focused around texture analysis, so each image sequence contains shadows moving in front of a number of various textured surfaces. The dataset contains four main subfolders: &quot;active&quot;, &quot;artificial&quot;, &quot;kondo&quot;, and&nbsp;&quot;static&quot;. The &quot;static&quot; folder contains ground-truthed image sequences of textured surfaces with shadows moving over them,&nbsp;and the &quot;active&quot; folder contains ground-truthed image sequences of a camera travelling over&nbsp;textured surfaces. The &quot;artificial&quot; folder contains a computer-generated 3D scene with computer-generated ground truth, but note that texture is absent from all images within. Finally, the &quot;kondo&quot; folder contains a series of extremely challenging images captured from a webcam mounted to a Kondo bipedal robot. This final dataset is challenging because it contains a high level of noise, flicker and interference from electrical lighting, and the&nbsp;poor&nbsp;lighting conditions make for complex shadows with large penumbrae.</p>
Share - Bookmark

  • Download from
    Zenodo via Zenodo (Dataset)
  • Cite this research data