The Library
Vidloc : a deep spatio-temporal model for 6-dof video-clip relocalization
Tools
Clark, Ronald, Wang, Sen, Markham, Andrew, Trigoni, Niki and Wen, Hongkai (2017) Vidloc : a deep spatio-temporal model for 6-dof video-clip relocalization. In: CVPR, Honolulu, Hawaii, 22-25 Jul 2017. Published in: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1 pp. 2652-2660. doi:10.1109/CVPR.2017.284
|
PDF
WRAP_1702.06521.pdf - Accepted Version - Requires a PDF viewer. Download (4Mb) | Preview |
Official URL: https://doi.org/10.1109/CVPR.2017.284
Abstract
Machine learning techniques, namely convolutional neural networks (CNN) and regression forests, have recently shown great promise in performing 6-DoF localization of monocular images. However, in most cases image-sequences, rather only single images, are readily available. To this extent, none of the proposed learning-based approaches exploit the valuable constraint of temporal smoothness, often leading to situations where the per-frame error is larger than the camera motion. In this paper we propose a recurrent model for performing 6-DoF localization of video-clips. We find that, even by considering only short sequences (20 frames), the pose estimates are smoothed and the localization error can be drastically reduced. Finally, we consider means of obtaining probabilistic pose estimates from our model. We evaluate our method on openly-available real-world autonomous driving and indoor localization datasets.
Item Type: | Conference Item (Paper) | ||||||
---|---|---|---|---|---|---|---|
Subjects: | Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software T Technology > TA Engineering (General). Civil engineering (General) |
||||||
Divisions: | Faculty of Science, Engineering and Medicine > Science > Computer Science | ||||||
Library of Congress Subject Headings (LCSH): | Computer vision -- Mathematical models, Depth of field (Photography) | ||||||
Journal or Publication Title: | 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) | ||||||
Publisher: | IEEE Computer Society | ||||||
Official Date: | 20 July 2017 | ||||||
Dates: |
|
||||||
Volume: | 1 | ||||||
Page Range: | pp. 2652-2660 | ||||||
DOI: | 10.1109/CVPR.2017.284 | ||||||
Status: | Peer Reviewed | ||||||
Publication Status: | Published | ||||||
Access rights to Published version: | Open Access (Creative Commons) | ||||||
Date of first compliant deposit: | 18 April 2017 | ||||||
Date of first compliant Open Access: | 18 April 2017 | ||||||
Conference Paper Type: | Paper | ||||||
Title of Event: | CVPR | ||||||
Type of Event: | Conference | ||||||
Location of Event: | Honolulu, Hawaii | ||||||
Date(s) of Event: | 22-25 Jul 2017 | ||||||
Related URLs: |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |
Downloads
Downloads per month over past year