UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

A New Object Scene Flow Algorithm Based on Support Points Selection and Robust Moving Object Proposal

Sun, Z; Lu, Z; Xue, J-H; Liao, Q; (2019) A New Object Scene Flow Algorithm Based on Support Points Selection and Robust Moving Object Proposal. In: Karam, Lina J and Mei, Tao and Wu, Feng, (eds.) Proceedings of the 2019 IEEE International Conference on Multimedia and Expo (ICME). IEEE Xplore Green open access

[img]
Preview
Text
ZhengyangSun-ICME2019.pdf - Accepted version

Download (1MB) | Preview

Abstract

Recent algorithms of object scene flow estimation suffer from low computational efficiency or unstable moving object proposals. To tackle these two problems simultaneously, in this paper we propose a new, efficient and robust algorithm for object scene flow estimation, through making two technical contributions. Firstly to improve the efficiency, we propose to select only a few pixels termed support points for matching cost calculation rather than using all pixels. The support points are defined as those pixels with high confidence in feature matching. Secondly to attain stable moving object proposals, we propose a motion magnitude-adaptive thresholding scheme for ego-motion outlier detection, after patch matching on CNN-extracted high quality features. These two contributions, though simple, ensure a remarkable improvement in both efficiency and accuracy from the original object scene flow method, as well as making the proposed algorithm a strong practicable alternative to much more sophisticated state-of-the-art competitors.

Type: Proceedings paper
Title: A New Object Scene Flow Algorithm Based on Support Points Selection and Robust Moving Object Proposal
ISBN: 978-1-5386-9552-4
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/icme.2019.00271
Publisher version: https://doi.org/10.1109/ICME.2019.00271
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: Proposals, Three-dimensional displays, Adaptive optics, Optical imaging, Estimation, Optical distortion, Feature extraction, Scene flow, Patch matching, Moving object proposal, Energy estimation
UCL classification: UCL
UCL > Provost and Vice Provost Offices
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science
URI: https://discovery.ucl.ac.uk/id/eprint/10079667
Downloads since deposit
27Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item