Content-sensitive Supervoxels via uniform tessellations on video manifolds

Yi, Ran, Liu, Yong-Jin and Lai, Yu-Kun ORCID: https://orcid.org/0000-0002-2094-5680 2018. Content-sensitive Supervoxels via uniform tessellations on video manifolds. Presented at: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Lake Salt City, USA, 18-22 June 2018.

Preview

PDF - Accepted Post-Print Version Download (2MB) | Preview

Abstract

Supervoxels are perceptually meaningful atomic regions in videos, obtained by grouping voxels that exhibit coherence in both appearance and motion. In this paper, we propose content-sensitive supervoxels (CSS), which are regularly-shaped 3D primitive volumes that possess the following characteristic: they are typically larger and longer in content-sparse regions (i.e., with homogeneous appearance and motion), and smaller and shorter in content-dense regions (i.e., with high variation of appearance and/or motion). To compute CSS, we map a video to a 3- dimensional manifold M embedded in R6, whose volume elements give a good measure of the content density in . We propose an efficient Lloyd-like method with a splittingmerging scheme to compute a uniform tessellation on M, which induces the CSS in . Theoretically our method has a good competitive ratio O(1). We also present a simple extension of CSS to stream CSS for processing long videos that cannot be loaded into main memory at once. We evaluate CSS, stream CSS and seven representative supervoxel methods on four video datasets. The results show that our method outperforms existing supervoxel methods.

Item Type:	Conference or Workshop Item (Paper)
Status:	In Press
Schools:	Computer Science & Informatics
ISSN:	2160-7508
Funders:	Royal Society
Date of First Compliant Deposit:	29 March 2018
Date of Acceptance:	19 February 2018
Last Modified:	23 Oct 2022 13:19
URI:	https://orca.cardiff.ac.uk/id/eprint/110339

Citation Data

Cited 6 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item