Watson, J;
Firman, M;
Monszpart, A;
Brostow, GJ;
(2020)
Footprints and free space from a single color image.
In:
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
(pp. pp. 11-20).
The Institute of Electrical and Electronics Engineers (IEEE)
Preview |
Text
2004.06376.pdf - Accepted Version Download (4MB) | Preview |
Abstract
Understanding the shape of a scene from a single color image is a formidable computer vision task. However, most methods aim to predict the geometry of surfaces that are visible to the camera, which is of limited use when planning paths for robots or augmented reality agents. Such agents can only move when grounded on a traversable surface, which we define as the set of classes which humans can also walk over, such as grass, footpaths and pavement. Models which predict beyond the line of sight often parameterize the scene with voxels or meshes, which can be expensive to use in machine learning frameworks. We introduce a model to predict the geometry of both visible and occluded traversable surfaces, given a single RGB image as input. We learn from stereo video sequences, using camera poses, per-frame depth and semantic segmentation to form training data, which is used to supervise an image-to-image network. We train models from the KITTI driving dataset, the indoor Matterport dataset, and from our own casually captured stereo footage. We find that a surprisingly low bar for spatial coverage of training scenes is required. We validate our algorithm against a range of strong baselines, and include an assessment of our predictions for a path-planning task
Type: | Proceedings paper |
---|---|
Title: | Footprints and free space from a single color image |
Event: | 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
ISBN-13: | 978-1-7281-7168-5 |
Open access status: | An open access version is available from UCL Discovery |
DOI: | 10.1109/CVPR42600.2020.00009 |
Publisher version: | https://doi.org/10.1109/CVPR42600.2020.00009 |
Language: | English |
Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions. |
Keywords: | Geometry, Cameras, Image segmentation, Color, Task analysis, Robot vision systems |
UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
URI: | https://discovery.ucl.ac.uk/id/eprint/10117261 |
Archive Staff Only
![]() |
View Item |