CaltechAUTHORS
  A Caltech Library Service

On Single-Sequence and Multi-Sequence Factorizations

Zelnik-Manor, Lihi and Irani, Michal (2006) On Single-Sequence and Multi-Sequence Factorizations. International Journal of Computer Vision, 67 (3). pp. 313-326. ISSN 0920-5691. https://resolver.caltech.edu/CaltechAUTHORS:20190823-105107960

[img] PDF - Submitted Version
See Usage Policy.

1127Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20190823-105107960

Abstract

Subspace based factorization methods are commonly used for a variety of applications, such as 3D reconstruction, multi-body segmentation and optical flow estimation. These are usually applied to a single video sequence. In this paper we present an analysis of the multi-sequence case and place it under a single framework with the single sequence case. In particular, we start by analyzing the characteristics of subspace based spatial and temporal segmentation. We show that in many cases objects moving with different 3D motions will be captured as a single object using multi-body (spatial) factorization approaches. Similarly, frames viewing different shapes might be grouped as displaying the same shape in the temporal factorization framework. Temporal factorization provides temporal grouping of frames by employing a subspace based approach to capture non-rigid shape changes (Zelnik-Manor and Irani, 2004). We analyze what causes these degeneracies and show that in the case of multiple sequences these can be made useful and provide information for both temporal synchronization of sequences and spatial matching of points across sequences.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1007/s11263-006-5157-4DOIArticle
https://rdcu.be/bPnyQPublisherFree ReadCube access
Additional Information:© Springer Science + Business Media, Inc 2006. Received February 4, 2005; Revised September 20, 2005; Accepted September 23, 2005. First online version published in March, 2006.
Subject Keywords:factorization; subspace based methods; multi-body segmentation; temporal synchronization; multi-sequence matching
Issue or Number:3
Record Number:CaltechAUTHORS:20190823-105107960
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20190823-105107960
Official Citation:Zelnik-Manor, L. & Irani, M. Int J Comput Vision (2006) 67: 313. https://doi.org/10.1007/s11263-006-5157-4
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:98173
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:23 Aug 2019 18:02
Last Modified:03 Oct 2019 21:38

Repository Staff Only: item control page