Fast and Compact Image Segmentation Using Instance Stixels

State-of-the-art stixel methods fuse dense stereo disparity and semantic class information, e.g., from a Convolutional Neural Network (CNN), into a compact representation of driveable space, obstacles and background. However, they do not explicitly differentiate instances within the same semantic class. The authors investigate several ways to augment single-frame stixels with instance information, which can be extracted by a CNN from the RGB image input. As a result, the authors' novel Instance Stixels method efficiently computes stixels that account for boundaries of individual objects, and represents instances as grouped stixels that express connectivity. Experiments on the Cityscapes dataset demonstrate that including instance information into the stixel computation itself, rather than as a post-processing step, increases the segmentation performance (i.e., Intersection over Union and Average Precision). This holds especially for overlapping objects of the same class. Furthermore, the authors show the superiority of their approach in terms of segmentation performance and computational efficiency compared to combining the separate outputs of Semantic Stixels and a state-of-the-art pixel-level CNN. The authors achieve processing throughput of 28 frames per second on average for 8 pixel wide stixels on images from the Cityscapes dataset at 1792 × 784 pixels. The authors' Instance Stixels software is made freely available for non-commercial research purposes.

Language

  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 01845047
  • Record Type: Publication
  • Files: TRIS
  • Created Date: May 10 2022 2:35PM