Instance stixels

Segmenting and grouping stixels into objects

Conference Paper (2019)
Author(s)

T.M. Hehn (TU Delft - Intelligent Vehicles)

J.F.P. Kooij (TU Delft - Intelligent Vehicles)

D. Gavrila (TU Delft - Intelligent Vehicles)

Research Group
Intelligent Vehicles
Copyright
© 2019 T.M. Hehn, J.F.P. Kooij, D. Gavrila
DOI related publication
https://doi.org/10.1109/IVS.2019.8814243
More Info
expand_more
Publication Year
2019
Language
English
Copyright
© 2019 T.M. Hehn, J.F.P. Kooij, D. Gavrila
Research Group
Intelligent Vehicles
Pages (from-to)
2542-2549
ISBN (electronic)
978-1-7281-0560-4
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

State-of-the-art stixel methods fuse dense stereo 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 class. We investigate several ways to augment single-frame stixels with instance information, which can similarly be extracted by a CNN from the color input. As a result, our novel Instance Stixels method efficiently computes stixels that do account for boundaries of individual objects, and represents individual instances as grouped stixels that express connectivity. Experiments on Cityscapes demonstrate that including instance information into the stixel computation itself, rather than as a post-processing step, increases Instance AP performance with approximately the same number of stixels. Qualitative results confirm that segmentation improves, especially for overlapping objects of the same class. Additional tests with ground truth instead of CNN output show that the approach has potential for even larger gains. Our Instance Stixels software is made freely available for non-commercial research purposes.

Files

Instance_Stixels_Segmenting_an... (pdf)
(pdf | 3.44 Mb)
- Embargo expired in 29-02-2020
License info not available